no code implementations • 25 Jun 2025 • Lei Zhu, Jun Zhou, Rick Siow Mong Goh, Yong liu
To this end, we propose to construct an auxiliary masked domain from original domain with masked image modeling and train the transformer to predict the entire segmentation mask with masked inputs to increase supervision signal.
no code implementations • 23 Jun 2025 • Xinyao Li, Jingjing Li, Fengling Li, Lei Zhu, Yang Yang, Heng Tao Shen
Popular benchmarks for VLM generalization are further introduced with thorough performance comparisons among the reviewed methods.
no code implementations • 19 Jun 2025 • Lei Zhu, Zhihao Yan, Hongbo Duan, Yongyang Cai, Xiaobing Zhang
This framework highlights the critical role of technology-sharing in fostering long-term climate cooperation under climate tipping uncertainties.
no code implementations • 12 Jun 2025 • Sixiang Chen, Jianyu Lai, Jialin Gao, Tian Ye, Haoyu Chen, Hengyu Shi, Shitong Shao, Yunlong Lin, Song Fei, Zhaohu Xing, Yeying Jin, Junfeng Luo, Xiaoming Wei, Lei Zhu
Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony.
no code implementations • 5 Jun 2025 • Yong Sun, Yipeng Wang, Junyu Shi, Zhiyuan Zhang, Yanmei Xiao, Lei Zhu, Manxi Jiang, Qiang Nie
To bridge this gap, we propose a new task called Video-Based Embryo Grading - the first paradigm that directly utilizes full-length time-lapse monitoring (TLM) videos to predict embryologists' overall quality assessments.
no code implementations • 29 May 2025 • Haoyu Chen, Keda Tao, Yizao Wang, Xinlei Wang, Lei Zhu, Jinjin Gu
Photo retouching is integral to photographic art, extending far beyond simple technical fixes to heighten emotional expression and narrative depth.
no code implementations • 26 May 2025 • Zongle Huang, Lei Zhu, Zongyuan Zhan, Ting Hu, Weikai Mao, Xianzhi Yu, Yongpan Liu, Tianyu Zhang
In this work, we first demonstrate that, under medium batch sizes, MoE surprisingly benefits more from SD than dense models.
no code implementations • 26 May 2025 • Zili Wang, Tianyu Zhang, Haoli Bai, Lu Hou, Xianzhi Yu, Wulong Liu, Shiming Xiang, Lei Zhu
By integrating these two approaches and allocating computational resources properly to each, our latency-optimal TTS enables a 32B model to reach 82. 3% accuracy on MATH-500 within 1 minute and a smaller 3B model to achieve 72. 4% within 10 seconds.
1 code implementation • 25 May 2025 • Lei Guo, Chenlong Song, Feng Guo, Xiaohui Han, Xiaojun Chang, Lei Zhu
Given the above challenges, we introduce the prompt learning technique for Many-to-one Non-overlapping Cross-domain Sequential Recommendation (MNCSR) and propose a Text-enhanced Co-attention Prompt Learning Paradigm (TCPLP).
no code implementations • 9 May 2025 • Henan Sun, Xunkai Li, Lei Zhu, Junyi Han, Guang Zeng, RongHua Li, Guoren Wang
In this paper, we advocate the learnable random walk (LRW) perspective as the instantiation of invariant knowledge, and propose LRW-OOD to realize graph OOD generalization learning.
1 code implementation • 6 May 2025 • Shuang Zeng, Chee Hong Lee, Micky C Nnamdi, Wenqi Shi, J Ben Tamo, Lei Zhu, Hangzhou He, Xinliang Zhang, Qian Chen, May D. Wang, Yanye Lu, Qiushi Ren
AttUKAN achieves F1 scores of 82. 50%, 81. 14%, 81. 34%, 80. 21% and 80. 09%, along with MIoU scores of 70. 24%, 68. 64%, 68. 59%, 67. 21% and 66. 94% in the above datasets, which are the highest compared to 11 networks for retinal vessel segmentation.
no code implementations • 25 Apr 2025 • Jiahao Huang, Fanwen Wang, Pedro F. Ferreira, Haosen Zhang, Yinzhe Wu, Zhifan Gao, Lei Zhu, Angelica I. Aviles-Rivero, Carola-Bibiane Schonlieb, Andrew D. Scott, Zohya Khalique, Maria Dwornik, Ramyah Rajakulasingam, Ranil De Silva, Dudley J. Pennell, Guang Yang, Sonia Nielles-Vallespin
Cardiac diffusion tensor imaging (DTI) offers unique insights into cardiomyocyte arrangements, bridging the gap between microscopic and macroscopic cardiac function.
no code implementations • 20 Apr 2025 • Jingjing Ren, Wenbo Li, Zhongdao Wang, Haoze Sun, Bangzhen Liu, Haoyu Chen, Jiaqi Xu, Aoxue Li, Shifeng Zhang, Bin Shao, Yong Guo, Lei Zhu
Compared to existing methods, Turbo2K is up to 20$\times$ faster for inference, making high-resolution video generation more scalable and practical for real-world applications.
no code implementations • 20 Apr 2025 • Shuang Zeng, Lei Zhu, Xinliang Zhang, Hangzhou He, Yanye Lu
Finally, experiments on 8 medical image datasets indicate our SuperCL outperforms existing 12 methods.
1 code implementation • 8 Apr 2025 • Sixiang Chen, Jinbin Bai, Zhuoran Zhao, Tian Ye, Qingyu Shi, Donghao Zhou, Wenhao Chai, Xin Lin, Jianzong Wu, Chao Tang, Shilin Xu, Tao Zhang, Haobo Yuan, Yikang Zhou, Wei Chow, Linfeng Li, Xiangtai Li, Lei Zhu, Lu Qi
The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to bridge understanding and generation tasks.
1 code implementation • 7 Apr 2025 • Bibek Poudel, Xuan Wang, Weizi Li, Lei Zhu, Kevin Heaslip
Reinforcement learning (RL) holds significant promise for adaptive traffic signal control.
1 code implementation • 29 Mar 2025 • Ziang Lu, Lei Guo, Xu Yu, Zhiyong Cheng, Xiaohui Han, Lei Zhu
In the evolving landscape of recommender systems, the challenge of effectively conducting privacy-preserving Cross-Domain Recommendation (CDR), especially under strict non-overlapping constraints, has emerged as a key focus.
no code implementations • CVPR 2025 • Haoyu Chen, Xiaojie Xu, Wenbo Li, Jingjing Ren, Tian Ye, Songhua Liu, Ying-Cong Chen, Lei Zhu, Xinchao Wang
To train our models, we develop the PosterArt dataset, comprising high-quality artistic posters annotated with layout, typography, and pixel-level stylized text segmentation.
2 code implementations • 18 Mar 2025 • Xinliang Zhang, Lei Zhu, Shuang Zeng, Hangzhou He, Ourui Fu, Zhengjian Yao, Zhaoheng Xie, Yanye Lu
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process.
1 code implementation • CVPR 2025 • Junjin Xiao, Qing Zhang, Yonewei Nie, Lei Zhu, Wei-Shi Zheng
To account for possible misalignment between SMPL model and images, we propose to predict image-aligned 3D prior points by leveraging both pixel-level features and voxel-level features, from which we regress the coarse Gaussians.
no code implementations • 17 Mar 2025 • Yu Liu, Hanbin Jiang, Lei Zhu, Yu Zhang, Yuqi Mao, Jiangxia Cao, Shuchao Pang
In the real world, users always have multiple interests while surfing different services to enrich their daily lives, e. g., watching hot short videos/live streamings.
no code implementations • 12 Mar 2025 • Yang Nan, Huichi Zhou, Xiaodan Xing, Giorgos Papanastasiou, Lei Zhu, Zhifan Gao, Alejandro F Fangi, Guang Yang
In this work, we propose a novel method to consolidate knowledge of hierarchical features and optimisation functions.
no code implementations • 7 Mar 2025 • Hongwei Yi, Tian Ye, Shitong Shao, Xuancheng Yang, Jiantong Zhao, Hanzhong Guo, Terrance Wang, Qingyu Yin, Zeke Xie, Lei Zhu, Wei Li, Michael Lingelbach, Daquan Zhou
We present MagicInfinite, a novel diffusion Transformer (DiT) framework that overcomes traditional portrait animation limitations, delivering high-fidelity results across diverse character types-realistic humans, full-body figures, and stylized anime characters.
no code implementations • 7 Mar 2025 • Lei Zhu, Yanyu Xu, Huazhu Fu, Xinxing Xu, Rick Siow Mong Goh, Yong liu
Specifically, our framework consists of a compact segmentation network with modality specific normalization layers for learning with partially labeled unpaired multi-modal data.
no code implementations • 1 Mar 2025 • Junjie Sheng, Jiehao Wu, Haochuan Cui, Yiqiu Hu, Wenli Zhou, Lei Zhu, Qian Peng, Wenhao Li, Xiangfeng Wang
This paper introduces a scalable RL framework, called Cluster Value Decomposition Reinforcement Learning (CVD-RL), to surmount the scalability hurdles inherent in large-scale VMS.
no code implementations • 16 Feb 2025 • Yunfei Liu, Lei Zhu, Lijian Lin, Ye Zhu, Ailing Zhang, Yu Li
3D facial reconstruction from a single in-the-wild image is a crucial task in human-centered computer vision tasks.
1 code implementation • 3 Feb 2025 • Zhizhen Zhang, Lei Zhu, Zhen Fang, Zi Huang, Yadan Luo
Pre-training vision-language representations on human action videos has emerged as a promising approach to reduce reliance on large-scale expert demonstrations for training embodied agents.
no code implementations • 29 Jan 2025 • Lei Zhu, Yuanqi Chen, Xiaohang Liu, Thomas H. Li, Ge Li
Our approach successfully addresses the issue of model-based methods' limitations in high-fidelity identity and the challenges faced by model-free methods in accurate motion transfer.
no code implementations • 22 Jan 2025 • Huilin Lai, Guang Zeng, Xunkai Li, Xudong Shen, Yinlin Zhu, Ye Luo, Jianwei Lu, Lei Zhu
Federated graph learning (FGL) has emerged as a promising paradigm for collaborative machine learning, enabling multiple parties to jointly train models while preserving the privacy of raw graph data.
1 code implementation • 9 Jan 2025 • Hangzhou He, Lei Zhu, Xinliang Zhang, Shuang Zeng, Qian Chen, Yanye Lu
Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification.
no code implementations • CVPR 2025 • Jianyu Lai, Sixiang Chen, Yunlong Lin, Tian Ye, Yun Liu, Song Fei, Zhaohu Xing, Hongtao Wu, Weiming Wang, Lei Zhu
Snowfall presents significant challenges for visual data processing, necessitating specialized desnowing algorithms.
1 code implementation • CVPR 2025 • Zhaohu Xing, Lihao Liu, Yijun Yang, Hongqiu Wang, Tian Ye, Sixiang Chen, Wenxue Li, Guang Liu, Lei Zhu
To effectively exploit this unlabeled dataset, we propose the first semi-supervised framework (namely an iterative data engine) consisting of four steps: (1) mirror detection model training, (2) pseudo label prediction, (3) dual guidance scoring, and (4) selection of highly reliable pseudo labels.
no code implementations • 24 Nov 2024 • Ruiqiang Xiao, Songning Lai, Yijun Yang, Jiemin Wu, Yutao Yue, Lei Zhu
The adaptation process has two stages: the first aligns the models on stable features using a mutual information consistency loss, and the second dynamically adjusts the perturbation level based on the loss from the first stage, encouraging the model to explore a broader range of the target domain while preserving existing performance.
1 code implementation • 21 Nov 2024 • Lei Zhu, Xinjiang Wang, Wayne Zhang, Rynson W. H. Lau
Specifically, in each layer, we use two different ways to represent an image: a fine-grained regular grid and a coarse-grained set of semantic slots.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
1 code implementation • 15 Nov 2024 • Shuai Gong, Chaoran Cui, Chunyun Zhang, Wenna Wang, Xiushan Nie, Lei Zhu
Specifically, we propose a novel FedDG framework through Prompt Learning and AggregatioN (PLAN), which comprises two training stages to collaboratively generate local prompts and global prompts at each federated round.
no code implementations • 13 Nov 2024 • ChengYuan Zhang, Yilin Zhang, Lei Zhu, Deyin Liu, Lin Wu, Bo Li, Shichao Zhang, Mohammed Bennamoun, Farid Boussaid
This paper introduces a novel framework for unified incremental few-shot object detection (iFSOD) and instance segmentation (iFSIS) using the Transformer architecture.
no code implementations • 6 Nov 2024 • Amer Essakine, Yanqi Cheng, Chun-Wun Cheng, Lipei Zhang, Zhongying Deng, Lei Zhu, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero
This survey serves as a roadmap for researchers, offering practical guidance for future exploration in the field of INRs.
1 code implementation • 6 Nov 2024 • Pedro R. A. S. Bassi, Wenxuan Li, Yucheng Tang, Fabian Isensee, Zifu Wang, Jieneng Chen, Yu-Cheng Chou, Yannick Kirchhoff, Maximilian Rokuss, Ziyan Huang, Jin Ye, Junjun He, Tassilo Wald, Constantin Ulrich, Michael Baumgartner, Saikat Roy, Klaus H. Maier-Hein, Paul Jaeger, Yiwen Ye, Yutong Xie, Jianpeng Zhang, Ziyang Chen, Yong Xia, Zhaohu Xing, Lei Zhu, Yousef Sadegheih, Afshin Bozorgpour, Pratibha Kumari, Reza Azad, Dorit Merhof, Pengcheng Shi, Ting Ma, Yuxin Du, Fan Bai, Tiejun Huang, Bo Zhao, Haonan Wang, Xiaomeng Li, Hanxue Gu, Haoyu Dong, Jichen Yang, Maciej A. Mazurowski, Saumya Gupta, Linshan Wu, Jiaxin Zhuang, Hao Chen, Holger Roth, Daguang Xu, Matthew B. Blaschko, Sergio Decherchi, Andrea Cavalli, Alan L. Yuille, Zongwei Zhou
We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.
1 code implementation • 25 Oct 2024 • Zixuan Gong, Guangyin Bao, Qi Zhang, Zhongwei Wan, Duoqian Miao, Shoujin Wang, Lei Zhu, Changwei Wang, Rongtao Xu, Liang Hu, Ke Liu, Yu Zhang
We contend that the key to addressing these challenges lies in accurately decoding both high-level semantics and low-level perception flows, as perceived by the brain in response to video stimuli.
1 code implementation • 20 Oct 2024 • Hao Chen, Lei Zhu, Xinghui Zhu
Deep hashing, due to its low cost and efficient retrieval advantages, is widely valued in cross-modal retrieval.
1 code implementation • 19 Oct 2024 • Hongqiu Wang, Zhaohu Xing, Weitong Wu, Yijun Yang, Qingqing Tang, Meixia Zhang, Yanwu Xu, Lei Zhu
Fundus imaging is a pivotal tool in ophthalmology, and different imaging modalities are characterized by their specific advantages.
1 code implementation • 12 Oct 2024 • Yunlu Yan, Lei Zhu, Yuexiang Li, Xinxing Xu, Rick Siow Mong Goh, Yong liu, Salman Khan, Chun-Mei Feng
However, existing fair FL methods ignore the specific characteristics of medical FL applications, i. e., domain shift among the datasets from different hospitals.
1 code implementation • 10 Oct 2024 • Hongtao Wu, Yijun Yang, Angelica I Aviles-Rivero, Jingjing Ren, Sixiang Chen, Haoyu Chen, Lei Zhu
Specifically, we construct a real-world dataset with 85 snowy videos, and then present a Semi-supervised Video Desnowing Network (SemiVDN) equipped by a novel Distribution-driven Contrastive Regularization.
Ranked #2 on
Snow Removal
on RVSD
(using extra training data)
1 code implementation • 10 Oct 2024 • Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng Yan
We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.
1 code implementation • 3 Oct 2024 • Zheng Zhang, Xu Yuan, Lei Zhu, Jingkuan Song, Liqiang Nie
In this paper, we introduce a novel bilateral backdoor to fill in the missing pieces of the puzzle in the cross-modal backdoor and propose a generalized invisible backdoor framework against cross-modal learning (BadCM).
no code implementations • 24 Sep 2024 • Sixiang Chen, Tian Ye, Kai Zhang, Zhaohu Xing, Yunlong Lin, Lei Zhu
Recent advancements in adverse weather restoration have shown potential, yet the unpredictable and varied combinations of weather degradations in the real world pose significant challenges.
no code implementations • 13 Sep 2024 • Zhaohu Xing, Sicheng Yang, Sixiang Chen, Tian Ye, Yijun Yang, Jing Qin, Lei Zhu
First, we propose a Modality-specific Representation Model (MRM) to model the distribution of target modalities.
1 code implementation • 11 Sep 2024 • Yingling Lu, Yijun Yang, Zhaohu Xing, Qiong Wang, Lei Zhu
We incorporate multi-task supervision into diffusion models to promote the discrimination of diffusion models on pixel-by-pixel segmentation.
no code implementations • 6 Sep 2024 • Hongqiu Wang, Yixian Chen, Wu Chen, Huihui Xu, Haoyu Zhao, Bin Sheng, Huazhu Fu, Guang Yang, Lei Zhu
Based on the above observations, we first devise a Serpentine Interwoven Adaptive (SIA) scan mechanism, which scans UWF-SLO images along curved vessel structures in a snake-like crawling manner.
no code implementations • 5 Sep 2024 • Lingyu Xiong, Xize Cheng, Jintao Tan, Xianjia Wu, Xiandong Li, Lei Zhu, Fei Ma, Minglei Li, Huang Xu, Zhihu Hu
Ultimately, we inject the previously generated talking segmentation and style codes into a mask-guided StyleGAN to synthesize video frame.
1 code implementation • 21 Aug 2024 • Haipeng Zhou, Honqiu Wang, Tian Ye, Zhaohu Xing, Jun Ma, Ping Li, Qiong Wang, Lei Zhu
Moreover, we are the first to introduce the Diffusion model for VSD in which we explore a Space-Time Encoded Embedding (STEE) to inject the temporal guidance for Diffusion to conduct shadow detection.
1 code implementation • 16 Aug 2024 • Hongqiu Wang, Wei Wang, Haipeng Zhou, Huihui Xu, Shaozhi Wu, Lei Zhu
Based on this dataset, we propose a Referring Shadow-Track Memory Network (RSM-Net) for addressing the RVSD task.
no code implementations • 3 Aug 2024 • Jintao Tan, Xize Cheng, Lingyu Xiong, Lei Zhu, Xiandong Li, Xianjia Wu, Kai Gong, Minglei Li, Yi Cai
Audio-driven talking head generation is a significant and challenging task applicable to various fields such as virtual avatars, film production, and online conferences.
1 code implementation • 31 Jul 2024 • Hongtao Wu, Yijun Yang, Huihui Xu, Weiming Wang, Jinni Zhou, Lei Zhu
Recently, the linear-complexity operator of the state space models (SSMs) has contrarily facilitated efficient long-term temporal modeling, which is crucial for rain streaks and raindrops removal in videos.
Ranked #1 on
Video deraining
on Video Waterdrop Removal Dataset
no code implementations • 25 Jul 2024 • Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Sixiang Chen, Tian Ye, Renjing Pei, Kaiwen Zhou, Fenglong Song, Lei Zhu
RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration.
no code implementations • 20 Jul 2024 • Yunlong Lin, Tian Ye, Sixiang Chen, Zhenqi Fu, Yingying Wang, Wenhao Chai, Zhaohu Xing, Lei Zhu, Xinghao Ding
Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications.
1 code implementation • 8 Jul 2024 • Huihui Xu, Yijun Yang, Angelica I Aviles-Rivero, Guang Yang, Jing Qin, Lei Zhu
To this end, we collect and annotate the first ultrasound video dataset with 100 videos for uterine fibroid segmentation (UFUV).
Ranked #1 on
Video Polyp Segmentation
on SUN-SEG-Easy
no code implementations • 2 Jul 2024 • Jingjing Ren, Wenbo Li, Haoyu Chen, Renjing Pei, Bin Shao, Yong Guo, Long Peng, Fenglong Song, Lei Zhu
Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands.
no code implementations • 19 Jun 2024 • Qian Chen, Lei Zhu, Hangzhou He, Xinliang Zhang, Shuang Zeng, Qiushi Ren, Yanye Lu
However, the incorrect pseudo-labels may corrupt the learned feature and lead to a new problem that the better the model is trained on the old task, the poorer the model performs on the new tasks.
1 code implementation • 19 Jun 2024 • Hongqiu Wang, Xiangde Luo, Wu Chen, Qingqing Tang, Mei Xin, Qiong Wang, Lei Zhu
In response, this study introduces a pioneering framework that leverages a patch-based active domain adaptation approach.
1 code implementation • 18 Jun 2024 • Junhao Lin, Lei Zhu, Jiaxing Shen, Huazhu Fu, Qing Zhang, Liansheng Wang
However, the existing salient object detection (SOD) works only focus on either static RGB-D images or RGB videos, ignoring the collaborating of RGB-D and video information.
1 code implementation • 17 Jun 2024 • Lei Zhu, Fangyun Wei, Yanye Lu, Dong Chen
We demonstrate the superior performance of our model over its counterparts across a variety of tasks, including image reconstruction, image classification, auto-regressive image generation using GPT, and image creation with diffusion- and flow-based generative models.
Ranked #12 on
Image Reconstruction
on ImageNet
no code implementations • 5 Jun 2024 • Qiang Nie, WeiFu Fu, Yuhuan Lin, Jialin Li, Yifeng Zhou, Yong liu, Lei Zhu, Chengjie Wang
Two issues have to be tackled in the new IIL setting: 1) the notorious catastrophic forgetting because of no access to old data, and 2) broadening the existing decision boundary to new observations because of concept drift.
no code implementations • 29 Apr 2024 • Liang Xu, Lei Zhu, Yaotong Wu, Hang Xue
The SuperCLUE-Fin (SC-Fin) benchmark is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs).
no code implementations • 19 Apr 2024 • Zixuan Gong, Qi Zhang, Guangyin Bao, Lei Zhu, Ke Liu, Liang Hu, Duoqian Miao
Decoding natural visual scenes from brain activity has flourished, with extensive research in single-subject tasks and, however, less in cross-subject tasks.
no code implementations • 19 Apr 2024 • Sheng Wang, Ge Sun, Fulong Ma, Tianshuai Hu, Qiang Qin, Yongkang Song, Lei Zhu, Junwei Liang
Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion.
1 code implementation • 17 Apr 2024 • Zhiyong Cheng, Jianhua Dong, Fan Liu, Lei Zhu, Xun Yang, Meng Wang
Furthermore, these models overlook the personalized nature of user behavioral preferences by employing uniform transformation networks for all users and items.
no code implementations • 8 Apr 2024 • Shuai Guo, Jielei Chu, Lei Zhu, Zhaoyu Li, Tianrui Li
This paper introduces a novel variant of GFNs, the Dynamic Backtracking GFN (DB-GFN), which improves the adaptability of decision-making steps through a reward-based dynamic backtracking mechanism.
no code implementations • CVPR 2024 • Haoyuan Wang, WenBo Hu, Lei Zhu, Rynson W. H. Lau
Our method has two stages: the geometry of the target object and the pre-filtered environmental radiance fields are reconstructed in the first stage, and materials of the target object are estimated in the second stage with the proposed NeP and material-aware cone sampling strategy.
no code implementations • 17 Mar 2024 • Zhihao Liang, Qi Zhang, WenBo Hu, Ying Feng, Lei Zhu, Kui Jia
This is because 3DGS treats each pixel as an isolated, single point rather than as an area, causing insensitivity to changes in the footprints of pixels.
1 code implementation • CVPR 2024 • Yijun Yang, Hongtao Wu, Angelica I. Aviles-Rivero, Yulun Zhang, Jing Qin, Lei Zhu
Although ViWS-Net is proposed to remove adverse weather conditions in videos with a single set of pre-trained weights, it is seriously blinded by seen weather at train-time and degenerates when coming to unseen weather during test-time.
1 code implementation • CVPR 2024 • Lei Zhu, Fangyun Wei, Yanye Lu
To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model.
1 code implementation • 8 Mar 2024 • Xinyao Li, Jingjing Li, Fengling Li, Lei Zhu, Ke Lu
Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models.
no code implementations • CVPR 2024 • Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Haoze Sun, Xueyi Zou, Zhensong Zhang, Youliang Yan, Lei Zhu
Leveraging unseen LR images for self-supervised learning guides the model to adapt its modeling space to the target domain, facilitating fine-tuning of SR models without requiring paired high-resolution (HR) images.
no code implementations • CVPR 2024 • Zhekai Du, Xinyao Li, Fengling Li, Ke Lu, Lei Zhu, Jingjing Li
Specifically, the image contextual information is utilized to prompt the language branch in a domain-agnostic and instance-conditioned way.
1 code implementation • 27 Feb 2024 • Xinliang Zhang, Lei Zhu, Hangzhou He, Lujia Jin, Yanye Lu
In this study, we propose a class-driven scribble promotion network, which utilizes both scribble annotations and pseudo-labels informed by image-level classes and global semantics for supervision.
no code implementations • 23 Feb 2024 • Francis Engelmann, Ayca Takmaz, Jonas Schult, Elisabetta Fedele, Johanna Wald, Songyou Peng, Xi Wang, Or Litany, Siyu Tang, Federico Tombari, Marc Pollefeys, Leonidas Guibas, Hongbo Tian, Chunjie Wang, Xiaosheng Yan, Bingwen Wang, Xuanyang Zhang, Xiao Liu, Phuc Nguyen, Khoi Nguyen, Anh Tran, Cuong Pham, Zhening Huang, Xiaoyang Wu, Xi Chen, Hengshuang Zhao, Lei Zhu, Joan Lasenby
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023.
1 code implementation • 22 Feb 2024 • Lei Zhu, Xinjiang Wang, Wayne Zhang, Rynson W. H. Lau
To eliminate such a redundancy, we propose RelayAttention, an attention algorithm that allows reading these hidden states from DRAM exactly once for a batch of input tokens.
no code implementations • 29 Jan 2024 • Jiahao Huang, Yinzhe Wu, Fanwen Wang, Yingying Fang, Yang Nan, Cagan Alkan, Daniel Abraham, Congyu Liao, Lei Xu, Zhifan Gao, Weiwen Wu, Lei Zhu, Zhaolin Chen, Peter Lally, Neal Bangerter, Kawin Setsompop, Yike Guo, Daniel Rueckert, Ge Wang, Guang Yang
Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans.
no code implementations • 28 Jan 2024 • Sharib Ali, Yamid Espinel, Yueming Jin, Peng Liu, Bianca Güttner, Xukun Zhang, Lihua Zhang, Tom Dowrick, Matthew J. Clarkson, Shiting Xiao, Yifan Wu, Yijun Yang, Lei Zhu, Dai Sun, Lan Li, Micha Pfeiffer, Shahid Farid, Lena Maier-Hein, Emmanuel Buc, Adrien Bartoli
A total of 6 teams from 4 countries participated, whose proposed methods were evaluated on 16 images and two preoperative 3D models from two patients.
1 code implementation • 25 Jan 2024 • Yijun Yang, Zhaohu Xing, Chunwang Huang, Lei Zhu
To this end, this paper presents a Video Vision Mamba-based framework, dubbed as Vivim, for medical video segmentation tasks.
1 code implementation • 24 Jan 2024 • Zhaohu Xing, Tian Ye, Yijun Yang, Guang Liu, Lei Zhu
Our SegMamba, in contrast to Transformer-based methods, excels in whole volume feature modeling from a state space model standpoint, maintaining superior processing speed, even with volume features at a resolution of {$64\times 64\times 64$}.
1 code implementation • 22 Jan 2024 • Liang Xu, Hang Xue, Lei Zhu, Kangkang Zhao
We introduce SuperCLUE-Math6(SC-Math6), a new benchmark dataset to evaluate the mathematical reasoning abilities of Chinese language models.
no code implementations • 16 Jan 2024 • Hao liu, Lei Guo, Lei Zhu, Yongqiang Jiang, Min Gao, Hongzhi Yin
To overcome the above challenges, we focus on NMCR, and devise MCRPL as our solution.
no code implementations • 5 Jan 2024 • Dongdi Zhao, Jianbo Ma, Lu Lu, Jinke Li, Xuan Ji, Lei Zhu, Fuming Fang, Ming Liu, Feijun Jiang
Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem.
no code implementations • 3 Jan 2024 • Jiawei Zhang, Yufan Chen, Cheng Jin, Lei Zhu, Yuantao Gu
Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks.
no code implementations • CVPR 2024 • Tian Ye, Sixiang Chen, Wenhao Chai, Zhaohu Xing, Jing Qin, Ge Lin, Lei Zhu
When adopting diffusion models for image restoration the crucial challenge lies in how to preserve high-level image fidelity in the randomness diffusion process and generate accurate background structures and realistic texture details.
no code implementations • 26 Dec 2023 • Jingjing Ren, Cheng Xu, Haoyu Chen, Xinran Qin, Lei Zhu
Recent progress in multi-modal conditioned face synthesis has enabled the creation of visually striking and accurately aligned facial images.
1 code implementation • 21 Dec 2023 • Yang Nan, Xiaodan Xing, Shiyi Wang, Zeyu Tang, Federico N Felder, Sheng Zhang, Roberta Eufrasia Ledda, Xiaoliu Ding, Ruiqi Yu, Weiping Liu, Feng Shi, Tianyang Sun, Zehong Cao, Minghui Zhang, Yun Gu, Hanxiao Zhang, Jian Gao, Pingyu Wang, Wen Tang, Pengxin Yu, Han Kang, Junqiang Chen, Xing Lu, Boyu Zhang, Michail Mamalakis, Francesco Prinzi, Gianluca Carlini, Lisa Cuneo, Abhirup Banerjee, Zhaohu Xing, Lei Zhu, Zacharia Mesbah, Dhruv Jain, Tsiry Mayet, Hongyu Yuan, Qing Lyu, Abdul Qayyum, Moona Mazher, Athol Wells, Simon LF Walsh, Guang Yang
The online validation set incorporated 52 HRCT scans from patients with fibrotic lung disease and the offline test set included 140 cases from fibrosis and COVID-19 patients.
1 code implementation • 15 Dec 2023 • Xiangde Luo, Jia Fu, Yunxin Zhong, Shuolin Liu, Bing Han, Mehdi Astaraki, Simone Bendazzoli, Iuliana Toma-Dasu, Yiwen Ye, Ziyang Chen, Yong Xia, Yanzhou Su, Jin Ye, Junjun He, Zhaohu Xing, Hongqiu Wang, Lei Zhu, Kaixiang Yang, Xin Fang, Zhiwei Wang, Chan Woong Lee, Sang Joon Park, Jaehee Chun, Constantin Ulrich, Klaus H. Maier-Hein, Nchongmaje Ndipenoch, Alina Miron, Yongmin Li, Yimeng Zhang, Yu Chen, Lu Bai, Jinlong Huang, Chengyang An, Lisheng Wang, Kaiwen Huang, Yunqi Gu, Tao Zhou, Mu Zhou, Shichuan Zhang, Wenjun Liao, Guotai Wang, Shaoting Zhang
The precise delineation of Gross Tumor Volumes (GTVs) and Organs-At-Risk (OARs) is crucial in radiation treatment, directly impacting patient prognosis.
1 code implementation • 6 Dec 2023 • Zixuan Gong, Qi Zhang, Guangyin Bao, Lei Zhu, Yu Zhang, Ke Liu, Liang Hu, Duoqian Miao
The limited data availability and the low signal-to-noise ratio of fMRI signals lead to the challenging task of fMRI-to-image retrieval.
no code implementations • 25 Nov 2023 • Ge Sun, Sheng Wang, Lei Zhu, Ming Liu, Jun Ma
To address these challenges and facilitate the use of diffusion models in multi-modal trajectory prediction, we propose GDTS, a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction.
no code implementations • 9 Oct 2023 • Liang Xu, Kangkang Zhao, Lei Zhu, Hang Xue
To systematically assess the safety of Chinese LLMs, we introduce SuperCLUE-Safety (SC-Safety) - a multi-round adversarial benchmark with 4912 open-ended questions covering more than 20 safety sub-dimensions.
1 code implementation • 3 Oct 2023 • Junhao Lin, Qian Dai, Lei Zhu, Huazhu Fu, Qiong Wang, Weibin Li, Wenhao Rao, Xiaoyang Huang, Liansheng Wang
We also devise a localization-based contrastive loss to reduce the lesion location distance between neighboring video frames within the same video and enlarge the location distances between frames from different ultrasound videos.
Ranked #3 on
Video Polyp Segmentation
on SUN-SEG-Easy
1 code implementation • ICCV 2023 • Yijun Yang, Angelica I. Aviles-Rivero, Huazhu Fu, Ye Liu, Weiming Wang, Lei Zhu
In this work, we propose the first framework for restoring videos from all adverse weather conditions by developing a video adverse-weather-component suppression network (ViWS-Net).
no code implementations • 21 Sep 2023 • Shuang Zeng, Lei Zhu, Xinliang Zhang, Qian Chen, Hangzhou He, Lujia Jin, Zifeng Tian, Qiushi Ren, Zhaoheng Xie, Yanye Lu
Moreover, we develop a multi-level contrastive learning strategy that integrates correspondences across feature-level, image-level, and pixel-level representations to ensure the encoder and decoder capture comprehensive details from representations of varying scales and granularities during the pre-training phase.
no code implementations • 18 Sep 2023 • Lei Zhu, Zhanghan Ke, Rynson Lau
In this work, we observe that the distribution gap between the confidence values of correct and incorrect pseudo labels emerges at the very beginning of the training, which can be utilized to filter pseudo labels.
1 code implementation • ICCV 2023 • Gang Fu, Qing Zhang, Lei Zhu, Chunxia Xiao, Ping Li
This paper aims to remove specular highlights from a single object-level image.
1 code implementation • 1 Sep 2023 • Zhening Huang, Xiaoyang Wu, Xi Chen, Hengshuang Zhao, Lei Zhu, Joan Lasenby
In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding.
Ranked #1 on
Zero-shot 3D Point Cloud Classification
on ScanNetV2
3D Open-Vocabulary Instance Segmentation
3D Open-Vocabulary Object Detection
+6
1 code implementation • 28 Aug 2023 • Tianshi Wang, Fengling Li, Lei Zhu, Jingjing Li, Zheng Zhang, Heng Tao Shen
With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval methods struggle to meet the needs of users seeking access to data across various modalities.
1 code implementation • ICCV 2023 • Sixiang Chen, Tian Ye, Jinbin Bai, ErKang Chen, Jun Shi, Lei Zhu
In the real world, image degradations caused by rain often exhibit a combination of rain streaks and raindrops, thereby increasing the challenges of recovering the underlying clean image.
no code implementations • 20 Aug 2023 • Yunlu Yan, Chun-Mei Feng, Yuexiang Li, Rick Siow Mong Goh, Lei Zhu
In this paper, we propose a novel communication-efficient federated learning framework, namely Fed-PMG, to address the missing modality challenge in federated multi-modal MRI reconstruction.
no code implementations • 20 Aug 2023 • Yunlu Yan, Chun-Mei Feng, Mang Ye, WangMeng Zuo, Ping Li, Rick Siow Mong Goh, Lei Zhu, C. L. Philip Chen
Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype.
no code implementations • 18 Aug 2023 • Hongqiu Wang, Lei Zhu, Guang Yang, Yike Guo, Shichen Zhang, Bo Xu, Yueming Jin
Our method is verified on these datasets, and experimental results exhibit that the VIS-Net can significantly outperform existing state-of-the-art referring segmentation methods.
no code implementations • 9 Aug 2023 • Lei Zhu, Hangzhou He, Xinliang Zhang, Qian Chen, Shuang Zeng, Qiushi Ren, Yanye Lu
Existing methods adopt an online-trained classification branch to provide pseudo annotations for supervising the segmentation branch.
no code implementations • 27 Jul 2023 • Liang Xu, Anqi Li, Lei Zhu, Hang Xue, Changtai Zhu, Kangkang Zhao, Haonan He, Xuanwei Zhang, Qiyue Kang, Zhenzhong Lan
We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE.
no code implementations • CVPR 2025 • Yunlu Yan, Huazhu Fu, Yuexiang Li, Jinheng Xie, Jun Ma, Guang Yang, Lei Zhu
In this paper, we focus on the feature distribution skewed FL scenario, a common non-IID situation in real-world applications where data from different clients exhibit varying underlying distributions.
no code implementations • 5 Jun 2023 • Yunlu Yan, Hong Wang, Yawen Huang, Nanjun He, Lei Zhu, Yuexiang Li, Yong Xu, Yefeng Zheng
To this end, we formulate this practical-yet-challenging cross-modal vertical federated learning task, in which shape data from multiple hospitals have different modalities with a small amount of multi-modality data collected from the same individuals.
no code implementations • 5 Jun 2023 • Hongqiu Wang, Yueming Jin, Lei Zhu
For robot-assisted surgery, an accurate surgical report reflects clinical operations during surgery and helps document entry tasks, post-operative analysis and follow-up treatment.
1 code implementation • 5 Jun 2023 • Junling Liu, Peilin Zhou, Yining Hua, Dading Chong, Zhongyu Tian, Andrew Liu, Helin Wang, Chenyu You, Zhenhua Guo, Lei Zhu, Michael Lingzhi Li
To the best of our knowledge, CMExam is the first Chinese medical exam dataset to provide comprehensive medical annotations.
no code implementations • 10 Apr 2023 • Zan Gao, Shenxun Wei, Weili Guan, Lei Zhu, Meng Wang, Shenyong Chen
Moreover, human semantic information and pedestrian identity information are not fully explored.
no code implementations • 9 Apr 2023 • Lei Guo, Chunxiao Wang, Xinhua Wang, Lei Zhu, Hongzhi Yin
Cross-domain Recommendation (CR) has been extensively studied in recent years to alleviate the data sparsity issue in recommender systems by utilizing different domain information.
1 code implementation • 28 Mar 2023 • Zhiyong Cheng, Sai Han, Fan Liu, Lei Zhu, Zan Gao, Yuxin Peng
Most existing multi-behavior models fail to capture such dependencies in a behavior chain for embedding learning.
1 code implementation • CVPR 2023 • Haoyu Chen, Jinjin Gu, Yihao Liu, Salma Abdel Magid, Chao Dong, Qiong Wang, Hanspeter Pfister, Lei Zhu
To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training.
1 code implementation • CVPR 2023 • Zhanghan Ke, Yuhao Liu, Lei Zhu, Nanxuan Zhao, Rynson W. H. Lau
In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed.
1 code implementation • 22 Mar 2023 • Haipeng Zhou, Lei Zhu, Yuyin Zhou
In order to explore its potential further, we have taken a step forward and considered a more complex scenario in the medical image domain, specifically, under an unsupervised adaptation condition.
1 code implementation • 19 Mar 2023 • Yijun Yang, Huazhu Fu, Angelica I. Aviles-Rivero, Carola-Bibiane Schönlieb, Lei Zhu
However, while a substantial amount of diffusion-based research has focused on generative tasks, few studies have applied diffusion models to general medical image classification.
1 code implementation • 18 Mar 2023 • Zhaohu Xing, Lei Zhu, Lequan Yu, Zhiheng Xing, Liang Wan
Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique.
1 code implementation • 18 Mar 2023 • Zhaohu Xing, Liang Wan, Huazhu Fu, Guang Yang, Lei Zhu
Our experimental results also indicate the universality and effectiveness of the proposed model.
1 code implementation • CVPR 2023 • Jiaqi Xu, Xiaowei Hu, Lei Zhu, Qi Dou, Jifeng Dai, Yu Qiao, Pheng-Ann Heng
Video dehazing aims to recover haze-free frames with high visibility and contrast.
no code implementations • 16 Mar 2023 • Zhihao Chen, Liang Wan, Yefan Xiao, Lei Zhu, Huazhu Fu
Then, we develop a progressive aggregation module to enhance the spatio and temporal characteristics of features maps, and effectively integrate the three kinds of features.
3 code implementations • CVPR 2023 • Lei Zhu, Xinjiang Wang, Zhanghan Ke, Wayne Zhang, Rynson Lau
As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency.
Ranked #9 on
Object Detection
on COCO 2017
(mAP metric)
no code implementations • 14 Mar 2023 • Zhening Huang, Xiaoyang Wu, Hengshuang Zhao, Lei Zhu, Shujun Wang, Georgios Hadjidemetriou, Ioannis Brilakis
For feature aggregation, it improves feature modeling by allowing the network to learn from both local points and neighboring geometry partitions, resulting in an enlarged data-tailored receptive field.
no code implementations • 23 Feb 2023 • Zhiqi Yu, Jingjing Li, Zhekai Du, Lei Zhu, Heng Tao Shen
Over the past decade, domain adaptation has become a widely studied branch of transfer learning that aims to improve performance on target domains by leveraging knowledge from the source domain.
2 code implementations • 12 Jan 2023 • Dawei Wang, Weizi Li, Lei Zhu, Jia Pan
We propose a decentralized multi-agent reinforcement learning approach for the control and coordination of mixed traffic by RVs at real-world, complex intersections -- an open challenge to date.
1 code implementation • ICCV 2023 • Haoyu Chen, Jingjing Ren, Jinjin Gu, Hongtao Wu, Xuequan Lu, Haoming Cai, Lei Zhu
We also develop a deep learning framework for video snow removal.
Ranked #4 on
Snow Removal
on RVSD
no code implementations • 29 Nov 2022 • Haochuan Cui, Junjie Sheng, Bo Jin, Yiqiu Hu, Li Su, Lei Zhu, Wenli Zhou, Xiangfeng Wang
With the rapid development of cloud computing, virtual machine scheduling has become one of the most important but challenging issues for the cloud computing community, especially for practical heterogeneous request sequences.
1 code implementation • 27 Nov 2022 • Zhengjie Huang, Zhenguang Liu, Jianhai Chen, Qinming He, Shuang Wu, Lei Zhu, Meng Wang
Meanwhile, decentralized applications have also attracted intense attention from the online gambling community, with more and more decentralized gambling platforms created through the help of smart contracts.
no code implementations • CVPR 2023 • Lihao Liu, Jean Prost, Lei Zhu, Nicolas Papadakis, Pietro Liò, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero
In this work, we argue that accounting for shadow deformation is essential when designing a video shadow detection method.
1 code implementation • 10 Nov 2022 • Liansheng Wang, Jiacheng Wang, Lei Zhu, Huazhu Fu, Ping Li, Gary Cheng, Zhipeng Feng, Shuo Li, Pheng-Ann Heng
Automated detecting lung infections from computed tomography (CT) data plays an important role for combating COVID-19.
no code implementations • 6 Sep 2022 • Li Wang, Xinyu Zhang, Wenyuan Qin, Xiaoyu Li, Lei Yang, Zhiwei Li, Lei Zhu, Hong Wang, Jun Li, Huaping Liu
As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection.
1 code implementation • 4 Sep 2022 • Tianling Liu, Wennan Liu, Lequan Yu, Liang Wan, Tong Han, Lei Zhu
Preoperative and noninvasive prediction of the meningioma grade is important in clinical practice, as it directly influences the clinical decision making.
1 code implementation • 31 Aug 2022 • Zhaohu Xing, Lequan Yu, Liang Wan, Tong Han, Lei Zhu
Multi-modal MR imaging is routinely used in clinical practice to diagnose and investigate brain tumors by providing rich complementary information.
1 code implementation • 16 Jul 2022 • Lei Zhu, Qian Chen, Lujia Jin, Yunfei You, Yanye Lu
Classification activation map (CAM), utilizing the classification structure to generate pixel-wise localization maps, is a crucial mechanism for weakly supervised object localization (WSOL).
1 code implementation • 4 Jul 2022 • Zhanghan Ke, Chunyi Sun, Lei Zhu, Ke Xu, Rynson W. H. Lau
Unlike prior methods that are based on black-box autoencoders, Harmonizer contains a neural network for filter argument prediction and several white-box filters (based on the predicted arguments) for image harmonization.
Ranked #7 on
Image Harmonization
on iHarmony4
2 code implementations • 1 Jul 2022 • Zhi Lin, Junhao Lin, Lei Zhu, Huazhu Fu, Jing Qin, Liansheng Wang
Moreover, we learn video-level features to classify the breast lesions of the original video as benign or malignant lesions to further enhance the final breast lesion detection performance in ultrasound videos.
1 code implementation • 16 Jun 2022 • Lei Guo, Jinyu Zhang, Li Tang, Tong Chen, Lei Zhu, Hongzhi Yin
Shared-account Cross-domain Sequential Recommendation (SCSR) task aims to recommend the next item via leveraging the mixed user behaviors in multiple domains.
no code implementations • 3 May 2022 • Zhenguang Liu, Sifan Wu, Chejian Xu, Xiang Wang, Lei Zhu, Shuang Wu, Fuli Feng
3) To enhance texture details, we encode facial features with geometric guidance and employ local GANs to refine the face, feet, and hands.
1 code implementation • CVPR 2022 • Xiaoxiao Liang, Yiqun Lin, Huazhu Fu, Lei Zhu, Xiaomeng Li
In this paper, we present a Random Sampling Consensus Federated learning, namely RSCFed, by considering the uneven reliability among models from fully-labeled clients, fully-unlabeled clients or partially labeled clients.
no code implementations • 21 Mar 2022 • Yiran Wei, Xi Chen, Lei Zhu, Lipei Zhang, Carola-Bibiane Schönlieb, Stephen J. Price, Chao Li
In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks.
1 code implementation • CVPR 2022 • Wenqiao Zhang, Lei Zhu, James Hallinan, Andrew Makmur, Shengyu Zhang, Qingpeng Cai, Beng Chin Ooi
In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can adaptively leverage the cluster assumption and consistency regularization of the unlabeled data according to the current learning status.
1 code implementation • CVPR 2022 • Lei Zhu, Qi She, Qian Chen, Yunfei You, Boyu Wang, Yanye Lu
To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects.
2 code implementations • IEEE Transactions on Medical Imaging 2022 • Mufeng Geng, Xiangxi Meng, Jiangyuan Yu, Lei Zhu, Lujia Jin, Zhe Jiang, Bin Qiu, Hui Li, Hanjing Kong, Jianmin Yuan, Kun Yang, Hongming Shan, Hongbin Han, Zhi Yang, Qiushi Ren, Yanye Lu
In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily.
no code implementations • 7 Jan 2022 • Pengxiang Su, Zhenguang Liu, Shuang Wu, Lei Zhu, Yifang Yin, Xuanjing Shen
In this paper, we introduce a novel convolutional neural model to effectively leverage explicit prior knowledge of motion anatomy, and simultaneously capture both spatial and temporal information of joint trajectory dynamics.
1 code implementation • 1 Jan 2022 • Xiaoqiang Wang, Lei Zhu, Siliang Tang, Huazhu Fu, Ping Li, Fei Wu, Yi Yang, Yueting Zhuang
The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data.
no code implementations • CVPR 2022 • Hongzu Su, Jingjing Li, Zhi Chen, Lei Zhu, Ke Lu
In this paper, we present a novel method which leverages both visual and semantic modalities to distinguish seen and unseen categories.
1 code implementation • 29 Dec 2021 • Lei Zhu, Qi She, Qian Chen, Xiangxi Meng, Mufeng Geng, Lujia Jin, Zhe Jiang, Bin Qiu, Yunfei You, Yibao Zhang, Qiushi Ren, Yanye Lu
In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively.
2 code implementations • 9 Dec 2021 • Junjie Sheng, Shengliang Cai, Haochuan Cui, Wenhao Li, Yun Hua, Bo Jin, Wenli Zhou, Yiqiu Hu, Lei Zhu, Qian Peng, Hongyuan Zha, Xiangfeng Wang
A novel simulator called VMAgent is introduced to help RL researchers better explore new methods, especially for virtual machine scheduling.
1 code implementation • 22 Nov 2021 • Lei Lin, Weizi Li, Lei Zhu
For instance, our model reduces MAE by 25. 3%, RMSE by 29. 2%, and MAPE by 20. 2%, compared to the state-of-the-art Diffusion Convolutional Recurrent Neural Network (DCRNN) model using the hourly dataset.
1 code implementation • 5 Nov 2021 • Ge-Peng Ji, Lei Zhu, Mingchen Zhuge, Keren Fu
Camouflaged Object Detection (COD) aims to detect objects with similar patterns (e. g., texture, intensity, colour, etc) to their surroundings, and recently has attracted growing research interest.
Ranked #15 on
Camouflaged Object Segmentation
on PCOD_1200
1 code implementation • 13 Oct 2021 • Fuming You, Jingjing Li, Lei Zhu, Ke Lu, Zhi Chen, Zi Huang
To address these problems, we investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain, and then adapting to the target domain without accessing source data anymore.
1 code implementation • 8 Oct 2021 • Jiacheng Wang, Lan Wei, Liansheng Wang, Qichao Zhou, Lei Zhu, Jing Qin
Skin lesion segmentation from dermoscopy images is of great importance for improving the quantitative analysis of skin cancer.
Ranked #5 on
Lesion Segmentation
on ISIC 2018
1 code implementation • 13 Sep 2021 • Yijun Yang, Shujun Wang, Lei Zhu, Lequan Yu
Particularly, for the Extrinsic Consistency, we leverage the knowledge across multiple source domains to enforce data-level consistency.
no code implementations • 9 Sep 2021 • Lei Zhu, Zhaojing Luo, Wei Wang, Meihui Zhang, Gang Chen, Kaiping Zheng
In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a label scarce target domain, thus potentially alleviates the annotation requirement for deep learning models.
1 code implementation • ICCV 2021 • Yujun Zhang, Lei Zhu, Wei Feng, Huazhu Fu, Mingqian Wang, Qingxia Li, Cheng Li, Song Wang
Lane detection plays a key role in autonomous driving.
1 code implementation • ICCV 2021 • Panhe Feng, Qi She, Lei Zhu, Jiaxin Li, Lin Zhang, Zijian Feng, Changhu Wang, Chunpeng Li, Xuejing Kang, Anlong Ming
Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image.
1 code implementation • 6 Aug 2021 • Ye Liu, Lei Zhu, Shunda Pei, Huazhu Fu, Jing Qin, Qing Zhang, Liang Wan, Wei Feng
Our DID-Net predicts the three component maps by progressively integrating features across scales, and refines each map by passing an independent refinement network.
Ranked #8 on
Image Dehazing
on Haze4k
1 code implementation • ICCV 2021 • Lei Zhu, Qi She, Duo Li, Yanye Lu, Xuejing Kang, Jie Hu, Changhu Wang
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks.
no code implementations • 2 Aug 2021 • Zhekai Du, Jingjing Li, Lei Zhu, Ke Lu, Heng Tao Shen
Energy disaggregation, also known as non-intrusive load monitoring (NILM), challenges the problem of separating the whole-home electricity usage into appliance-specific individual consumptions, which is a typical application of data analysis.
1 code implementation • 23 Jun 2021 • Mengdi Gao, Ximeng Feng, Mufeng Geng, Zhe Jiang, Lei Zhu, Xiangxi Meng, Chuanqing Zhou, Qiushi Ren, Yanye Lu
BLRM utilizes maximum a posteriori probability (MAP) in the Bayesian statistics and the exponentially time-weighted technique to selectively correct the labels of noisy images.
no code implementations • CVPR 2021 • Gang Fu, Qing Zhang, Lei Zhu, Ping Li, Chunxia Xiao
Specular highlight detection and removal are fundamental and challenging tasks.
1 code implementation • 17 Jun 2021 • Zhenguang Liu, Peng Qian, Xiang Wang, Lei Zhu, Qinming He, Shouling Ji
In this paper, we explore combining deep learning with expert patterns in an explainable fashion.
2 code implementations • CVPR 2021 • Zhekai Du, Jingjing Li, Hongzu Su, Lei Zhu, Ke Lu
Previous bi-classifier adversarial learning methods only focus on the similarity between the outputs of two distinct classifiers.
1 code implementation • 10 May 2021 • Xinxiao Zhao, Zhiyong Cheng, Lei Zhu, Jiecai Zheng, Xueqing Li
In particular, for a directed relation, we transform the head and tail entities into the corresponding relation space to model their relation; and for an undirected co-occurrence relation, we project head and tail entities into a unique hyperplane in the entity space to minimize their distance.
no code implementations • 7 May 2021 • Lei Guo, Li Tang, Tong Chen, Lei Zhu, Quoc Viet Hung Nguyen, Hongzhi Yin
Shared-account Cross-domain Sequential recommendation (SCSR) is the task of recommending the next item based on a sequence of recorded user behaviors, where multiple users share a single account, and their behaviours are available in multiple domains.
no code implementations • 5 Apr 2021 • Cheng Xue, Lei Zhu, Huazhu Fu, Xiaowei Hu, Xiaomeng Li, Hai Zhang, Pheng Ann Heng
The BD modules learn additional breast lesion boundary map to enhance the boundary quality of a segmentation result refinement.
1 code implementation • CVPR 2021 • Lei Zhu, Qi She, Bin Zhang, Yanye Lu, Zhilin Lu, Duo Li, Jie Hu
Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence.
1 code implementation • CVPR 2021 • Zhihao Chen, Liang Wan, Lei Zhu, Jia Shen, Huazhu Fu, Wennan Liu, Jing Qin
The bottleneck is the lack of a well-established dataset with high-quality annotations for video shadow detection.
13 code implementations • CVPR 2021 • Duo Li, Jie Hu, Changhu Wang, Xiangtai Li, Qi She, Lei Zhu, Tong Zhang, Qifeng Chen
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision.
Ranked #765 on
Image Classification
on ImageNet
1 code implementation • 22 Feb 2021 • Zhiyong Cheng, Fan Liu, Shenghan Mei, Yangyang Guo, Lei Zhu, Liqiang Nie
To demonstrate the effectiveness of our method, we design a light attention neural network to integrate both item-level and feature-level attention for neural ICF models.
1 code implementation • 19 Feb 2021 • Fan Liu, Zhiyong Cheng, Lei Zhu, Zan Gao, Liqiang Nie
To form the subgraphs, we design an unsupervised subgraph generation module, which can effectively identify users with common interests by exploiting both user feature and graph structure.
no code implementations • 5 Feb 2021 • Jingjing Ren, Xiaowei Hu, Lei Zhu, Xuemiao Xu, Yangyang Xu, Weiming Wang, Zijun Deng, Pheng-Ann Heng
Camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings.
no code implementations • 1 Jan 2021 • Lei Zhu, Qi She, Changhu Wang
When choosing Chebyshev graph filter, a generalized formulation can be derived for explaining the existing nonlocal-based blocks (e. g. nonlocal block, nonlocal stage, double attention block) and uses to analyze their irrationality.
no code implementations • ICCV 2021 • Lei Zhu, Ke Xu, Zhanghan Ke, Rynson W.H. Lau
These two phenomenons reveal that deep shadow detectors heavily depend on the intensity cue, which we refer to as intensity bias.
Ranked #1 on
Shadow Detection
on CUHK-Shadow
no code implementations • 17 Oct 2020 • Zhaojing Luo, Sai Ho Yeung, Meihui Zhang, Kaiping Zheng, Lei Zhu, Gang Chen, Feiyi Fan, Qian Lin, Kee Yuan Ngiam, Beng Chin Ooi
In this paper, we identify two main challenges that arise during the deployment of machine learning pipelines, and address them with the design of versioning for an end-to-end analytics system MLCask.
no code implementations • 10 Oct 2020 • Gang Fu, Qing Zhang, QiFeng Lin, Lei Zhu, and Chunaxia Xiao
Specular highlight detection is a challenging problem, and has many applications such as shiny object detection and light source estimation.
1 code implementation • 10 Jun 2020 • Lei Zhu, Hui Cui, Zhiyong Cheng, Jingjing Li, Zheng Zhang
Specifically, we design a complementary dual-level semantic transfer mechanism to efficiently discover the potential semantics of tags and seamlessly transfer them into binary hash codes.
no code implementations • 8 Apr 2020 • Youyi Song, Lei Zhu, Baiying Lei, Bin Sheng, Qi Dou, Jing Qin, Kup-Sze Choi
In the shape evolution, we compensate intensity deficiency for the segmentation by introducing not only the modeled local shape priors but also global shape priors (clump--level) modeled by considering mutual shape constraints of cytoplasms in the clump.
no code implementations • 1 Apr 2020 • Fengling Li, Tong Wang, Lei Zhu, Zheng Zhang, Xinhua Wang
Unlike previous cross-modal hashing approaches, our learning framework jointly optimizes semantic preserving that transforms deep features of multimedia data into binary hash codes, and the semantic regression which directly regresses query modality representation to explicit label.
no code implementations • 24 Mar 2020 • Yang Xu, Lei Zhu, Zhiyong Cheng, Jingjing Li, Jiande Sun
Additionally, we develop a fast discrete optimization algorithm to directly compute the binary hash codes with simple operations.
no code implementations • 23 Mar 2020 • Tobias Ross, Annika Reinke, Peter M. Full, Martin Wagner, Hannes Kenngott, Martin Apitz, Hellena Hempe, Diana Mindroc Filimon, Patrick Scholz, Thuy Nuong Tran, Pierangela Bruno, Pablo Arbeláez, Gui-Bin Bian, Sebastian Bodenstedt, Jon Lindström Bolmgren, Laura Bravo-Sánchez, Hua-Bin Chen, Cristina González, Dong Guo, Pål Halvorsen, Pheng-Ann Heng, Enes Hosgor, Zeng-Guang Hou, Fabian Isensee, Debesh Jha, Tingting Jiang, Yueming Jin, Kadir Kirtac, Sabrina Kletz, Stefan Leger, Zhixuan Li, Klaus H. Maier-Hein, Zhen-Liang Ni, Michael A. Riegler, Klaus Schoeffmann, Ruohua Shi, Stefanie Speidel, Michael Stenzel, Isabell Twick, Gutai Wang, Jiacheng Wang, Liansheng Wang, Lu Wang, Yu-Jie Zhang, Yan-Jie Zhou, Lei Zhu, Manuel Wiesenfarth, Annette Kopp-Schneider, Beat P. Müller-Stich, Lena Maier-Hein
The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data.
no code implementations • 20 Mar 2020 • Fan Liu, Zhiyong Cheng, Lei Zhu, Chenghao Liu, Liqiang Nie
Considering the fact that for different users, the attributes of an item have different influence on their preference for this item, we design a novel attention mechanism to filter the message passed from an item to a target user by considering the attribute information.
no code implementations • 18 Dec 2019 • Tianyu Zhang, Lei Zhu, Qian Zhao, Kilho Shin
Quantization of weights of deep neural networks (DNN) has proven to be an effective solution for the purpose of implementing DNNs on edge devices such as mobiles, ASICs and FPGAs, because they have no sufficient resources to support computation involving millions of high precision weights and multiply-accumulate operations.
no code implementations • 26 Nov 2019 • Panhe Feng, Xuejing Kang, Lizhu Ye, Lei Zhu, Chunpeng Li, Anlong Ming
Besides, considering the restriction of occlusion orientation presentation to occlusion orientation learning, we design a new orthogonal representation for occlusion orientation and proposed the Orthogonal Orientation Regression loss which can get rid of the unfitness between occlusion representation and learning and further prompt the occlusion orientation learning.
no code implementations • 4 Nov 2019 • Lei Zhu, Qi She, Lidan Zhang, Ping Guo
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks.
1 code implementation • 4 Nov 2019 • Xiaomeng Li, Xiao-Wei Hu, Lequan Yu, Lei Zhu, Chi-Wing Fu, Pheng-Ann Heng
In this paper, we present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring the internal relationship between the diseases with only image-level supervision.
no code implementations • 25 Sep 2019 • Lei Zhu, Wei Wang, Mei Hui Zhang, Beng Chin Ooi, Chang Yao
State-of-the-art Unsupervised Domain Adaptation (UDA) methods learn transferable features by minimizing the feature distribution discrepancy between the source and target domains.
no code implementations • 25 Sep 2019 • Lei Zhu, Qi She, Lidan Zhang, Ping Guo
The nonlocal network is designed for capturing long-range spatial-temporal dependencies in several computer vision tasks.
1 code implementation • 17 Sep 2019 • Jingjing Li, Mengmeng Jing, Ke Lu, Lei Zhu, Yang Yang, Zi Huang
An inevitable issue of such a paradigm is that the synthesized unseen features are prone to seen references and incapable to reflect the novelty and diversity of real unseen instances.
1 code implementation • 17 Sep 2019 • Jingjing Li, Erpeng Chen, Zhengming Ding, Lei Zhu, Ke Lu, Zi Huang
Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions.
Ranked #4 on
Domain Adaptation
on USPS-to-MNIST
1 code implementation • 27 Aug 2019 • Yinwei Wei, Zhiyong Cheng, Xuzheng Yu, Zhou Zhao, Lei Zhu, Liqiang Nie
The hashtags, that a user provides to a post (e. g., a micro-video), are the ones which in her mind can well describe the post content where she is interested in.
no code implementations • 25 Jul 2019 • Qing Zhang, Yongwei Nie, Lei Zhu, Chunxia Xiao, Wei-Shi Zheng
To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency.
no code implementations • 3 Jul 2019 • Lihao Liu, Xiaowei Hu, Lei Zhu, Pheng-Ann Heng
This paper presents a novel framework for unsupervised 3D brain image registration by capturing the feature-level transformation relationships between the unaligned image and reference image.
1 code implementation • 3 Jul 2019 • Yi Wang, Haoran Dou, Xiao-Wei Hu, Lei Zhu, Xin Yang, Ming Xu, Jing Qin, Pheng-Ann Heng, Tianfu Wang, Dong Ni
Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers.
1 code implementation • 20 Jun 2019 • Jingjing Li, Mengmeng Jing, Ke Lu, Lei Zhu, Yang Yang, Zi Huang
This work, for the first time, formulates CSR as a ZSL problem, and a tailor-made ZSL method is proposed to handle CSR.
no code implementations • 5 Jun 2019 • Chengyuan Zhang, Lei Zhu, Shichao Zhang
In this paper, we introduce a novel unsupervised pose augmentation cross-view person Re-Id scheme called PAC-GAN to overcome these limitations.
Cross-Modal Person Re-Identification
Generative Adversarial Network
+2
no code implementations • 25 Apr 2019 • Li Wang, Lei Zhu, En Yu, Jiande Sun, Huaxiang Zhang
Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages.
no code implementations • 25 Apr 2019 • Lei Zhu, Zi Huang, Zhihui Li, Liang Xie, Heng Tao Shen
To address the problem, in this paper, we propose a novel hashing approach, dubbed as \emph{Discrete Semantic Transfer Hashing} (DSTH).
1 code implementation • 25 Apr 2019 • Yudong Han, Lei Zhu, Zhiyong Cheng, Jingjing Li, Xiaobai Liu
2) the relaxing process of cluster labels may cause significant information loss.