no code implementations • NLP4ConvAI (ACL) 2022 • Tong Zhang, Yong liu, Boyang Li, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao
Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.
1 code implementation • EMNLP 2021 • Hao Zhou, Minlie Huang, Yong liu, Wei Chen, Xiaoyan Zhu
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems.
1 code implementation • 16 Apr 2024 • Jiangning Zhang, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Zhucun Xue, Yong liu, Guansong Pang, DaCheng Tao
Moreover, current metrics such as AU-ROC have nearly reached saturation on simple datasets, which prevents a comprehensive evaluation of different methods.
no code implementations • 10 Apr 2024 • Jiahao Wang, Wenqi Shao, Mengzhao Chen, Chengyue Wu, Yong liu, Kaipeng Zhang, Songyang Zhang, Kai Chen, Ping Luo
We first "LLaMAfy" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a casual mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training.
1 code implementation • 1 Apr 2024 • Jiazheng Xing, Chao Xu, Yijie Qian, Yang Liu, Guang Dai, Baigui Sun, Yong liu, Jingdong Wang
However, the clothing identity uncontrollability and training inefficiency of existing diffusion-based methods, which struggle to maintain the identity even with full parameter training, are significant limitations that hinder the widespread applications.
no code implementations • 28 Mar 2024 • Haonan Lin, Mengmeng Wang, Yan Chen, Wenbin An, Yuzhe Yao, Guang Dai, Qianying Wang, Yong liu, Jingdong Wang
While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centered images, novel challenges arise with a nuanced task of "identity fine editing": precisely modifying specific features of a subject while maintaining its inherent identity and context.
no code implementations • 26 Mar 2024 • Yongqiang Han, Hao Wang, Kefan Wang, Likang Wu, Zhi Li, Wei Guo, Yong liu, Defu Lian, Enhong Chen
In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to a cart, and purchasing.
1 code implementation • 24 Mar 2024 • Xiaojun Hou, Jiazheng Xing, Yijie Qian, Yaowei Guo, Shuo Xin, JunHao Chen, Kai Tang, Mengmeng Wang, Zhengkai Jiang, Liang Liu, Yong liu
Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness.
no code implementations • 21 Mar 2024 • Xi Jiang, Ying Chen, Qiang Nie, Jianlin Liu, Yong liu, Chengjie Wang, Feng Zheng
To address this issue, we introduce a Multi-class Implicit Neural representation Transformer for unified Anomaly Detection (MINT-AD), which leverages the fine-grained category information in the training stage.
1 code implementation • NeurIPS 2022 • Xi Jiang, Ying Chen, Qiang Nie, Yong liu, Jianlin Liu, Bin-Bin Gao, Jun Liu, Chengjie Wang, Feng Zheng
Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction.
no code implementations • 21 Mar 2024 • Yulan Hu, Sheng Ouyang, Zhirui Yang, Ge Chen, Junchen Wan, Xiao Wang, Yong liu
Specifically, GA^2E proposes to use the subgraph as the meta-structure, which remains consistent across all graph tasks (ranging from node-, edge-, and graph-level to transfer learning) and all stages (both during training and inference).
no code implementations • 19 Mar 2024 • Pengzhi Li, Qiang Nie, Ying Chen, Xi Jiang, Kai Wu, Yuhuan Lin, Yong liu, Jinlong Peng, Chengjie Wang, Feng Zheng
To our knowledge, this is the first tuning-free method that concurrently utilizes text and image guidance for image customization in specific regions.
no code implementations • 19 Mar 2024 • Ying Chen, Yong liu, Kai Wu, Qiang Nie, Shang Xu, Huifang Ma, Bing Wang, Chengjie Wang
Deep learning-based image matching methods play a crucial role in computer vision, yet they often suffer from substantial computational demands.
no code implementations • 17 Mar 2024 • Yixiang Mao, Liyang Sun, Yong liu, Yao Wang
We develop a low-latency FoV-adaptive coding and streaming system for interactive applications that is robust to bandwidth variations and FoV prediction errors.
no code implementations • 13 Mar 2024 • Siqi Li, Jun Chen, Jingyang Xiang, Chengrui Zhu, Yong liu
AutoDFP assesses the similarity of channels for each layer and provides this information to the reinforcement learning agent, guiding the pruning and reconstruction process of the network.
no code implementations • 9 Mar 2024 • Xiuzhe Wu, Xiaoyang Lyu, Qihao Huang, Yong liu, Yang Wu, Ying Shan, Xiaojuan Qi
Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion.
no code implementations • 8 Mar 2024 • Tanvi Verma, Linh Le Dinh, Nicholas Tan, Xinxing Xu, ChingYu Cheng, Yong liu
During the test, a patient's gaze is fixed at a specific location while light stimuli of varying intensities are presented in central and peripheral vision.
no code implementations • 7 Mar 2024 • Jialin Li, Qiang Nie, WeiFu Fu, Yuhuan Lin, Guangpin Tao, Yong liu, Chengjie Wang
Deep learning models, particularly those based on transformers, often employ numerous stacked structures, which possess identical architectures and perform similar functions.
no code implementations • 7 Mar 2024 • Wenjie Wang, Yang Zhang, Xinyu Lin, Fuli Feng, Weiwen Liu, Yong liu, Xiangyu Zhao, Wayne Xin Zhao, Yang song, Xiangnan He
The rise of generative models has driven significant advancements in recommender systems, leaving unique opportunities for enhancing users' personalized recommendations.
no code implementations • 29 Feb 2024 • Yuxuan Wang, Haixu Wu, Jiaxiang Dong, Yong liu, Yunzhong Qiu, Haoran Zhang, Jianmin Wang, Mingsheng Long
Experimentally, TimeXer significantly improves time series forecasting with exogenous variables and achieves consistent state-of-the-art performance in twelve real-world forecasting benchmarks.
1 code implementation • 29 Feb 2024 • Chen Qian, Jie Zhang, Wei Yao, Dongrui Liu, Zhenfei Yin, Yu Qiao, Yong liu, Jing Shao
This research provides an initial exploration of trustworthiness modeling during LLM pre-training, seeking to unveil new insights and spur further developments in the field.
no code implementations • 24 Feb 2024 • Yong liu, Zirui Zhu, Chaoyu Gong, Minhao Cheng, Cho-Jui Hsieh, Yang You
While fine-tuning large language models (LLMs) for specific tasks often yields impressive results, it comes at the cost of memory inefficiency due to back-propagation in gradient-based training.
1 code implementation • 23 Feb 2024 • Zirui Zhu, Yong liu, Zangwei Zheng, Huifeng Guo, Yang You
We explore the typical data characteristics and optimization statistics of CTR prediction, revealing a strong positive correlation between the top hessian eigenvalue and feature frequency.
no code implementations • 17 Feb 2024 • Hongye Zeng, Ke Zou, Zhihao Chen, Yuchong Gao, Hongbo Chen, Haibin Zhang, Kang Zhou, Meng Wang, Rick Siow Mong Goh, Yong liu, Chang Jiang, Rui Zheng, Huazhu Fu
Moreover, the models trained on standard ultrasound device data are constrained by training data distribution and perform poorly when directly applied to handheld device data.
no code implementations • 15 Feb 2024 • Dexun Li, Cong Zhang, Kuicai Dong, Derrick Goh Xin Deik, Ruiming Tang, Yong liu
In this paper, we introduce the Distributional Preference Reward Model (DPRM), a simple yet effective framework to align large language models with a diverse set of human preferences.
1 code implementation • 4 Feb 2024 • Yong liu, Guo Qin, Xiangdong Huang, Jianmin Wang, Mingsheng Long
Foundation models of time series have not been fully developed due to the limited availability of large-scale time series and the underexploration of scalable pre-training.
1 code implementation • 4 Feb 2024 • Yong liu, Haoran Zhang, Chenyu Li, Xiangdong Huang, Jianmin Wang, Mingsheng Long
Continuous progresses have been achieved as the emergence of large language models, exhibiting unprecedented ability in few-shot generalization, scalability, and task generality, which is however absent in time series models.
1 code implementation • 3 Feb 2024 • Han Li, Yukai Ma, Yuehao Huang, Yaqing Gu, Weihua Xu, Yong liu, Xingxing Zuo
Dense depth recovery is crucial in autonomous driving, serving as a foundational element for obstacle avoidance, 3D object detection, and local path planning.
1 code implementation • 25 Jan 2024 • Mathieu Ravaut, Hao Zhang, Lu Xu, Aixin Sun, Yong liu
Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation.
no code implementations • 22 Jan 2024 • Xunyu Zhu, Jian Li, Yong liu, Can Ma, Weiping Wang
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance.
no code implementations • 22 Jan 2024 • Mengmeng Wang, Jiazheng Xing, Boyuan Jiang, Jun Chen, Jianbiao Mei, Xingxing Zuo, Guang Dai, Jingdong Wang, Yong liu
In this paper, we introduce a novel Multimodal, Multi-task CLIP adapting framework named \name to address these challenges, preserving both high supervised performance and robust transferability.
no code implementations • 14 Jan 2024 • Junyu Zhu, Lina Liu, Bofeng Jiang, Feng Wen, Hongbo Zhang, Wanlong Li, Yong liu
In this paper, to lower the annotation cost, we propose a self-supervised event-based monocular depth estimation framework named EMoDepth.
no code implementations • 10 Jan 2024 • Yong Ma, Senlin Luo, Yu-Ming Shang, ZhengJun Li, Yong liu
The verbalizer, which serves to map label words to class labels, is an essential component of prompt-tuning.
1 code implementation • 9 Jan 2024 • Han Li, Yukai Ma, Yaqing Gu, Kewei Hu, Yong liu, Xingxing Zuo
To circumvent this issue, we learn to augment versatile and robust monocular depth prediction with the dense metric scale induced from sparse and noisy Radar data.
1 code implementation • 5 Jan 2024 • Jian Li, Yong liu, Wei Wang, Haoran Wu, Weiping Wang
We provide convergence analysis based on statistical learning for the federated Newton sketch approaches.
1 code implementation • 3 Jan 2024 • Zitong Huang, Ze Chen, Zhixing Chen, Erjin Zhou, Xinxing Xu, Rick Siow Mong Goh, Yong liu, WangMeng Zuo, ChunMei Feng
When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge.
1 code implementation • 2 Jan 2024 • Jiaqi Liu, Kai Wu, Qiang Nie, Ying Chen, Bin-Bin Gao, Yong liu, Jinbao Wang, Chengjie Wang, Feng Zheng
Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible.
1 code implementation • 1 Jan 2024 • Zhuoyan Luo, Yicheng Xiao, Yong liu, Yitong Wang, Yansong Tang, Xiu Li, Yujiu Yang
The recent transformer-based models have dominated the Referring Video Object Segmentation (RVOS) task due to the superior performance.
1 code implementation • 31 Dec 2023 • Yue Han, Jiangning Zhang, Junwei Zhu, Xiangtai Li, Yanhao Ge, Wei Li, Chengjie Wang, Yong liu, Xiaoming Liu, Ying Tai
This work presents FaceX framework, a novel facial generalist model capable of handling diverse facial tasks simultaneously.
1 code implementation • 27 Dec 2023 • Tianxin Huang, Qingyao Liu, Xiangrui Zhao, Jun Chen, Yong liu
As point clouds are 3D signals with permutation invariance, most existing works train their reconstruction networks by measuring shape differences with the average point-to-point distance between point clouds matched with predefined rules.
1 code implementation • 21 Dec 2023 • Xianfang Zeng, Xin Chen, Zhongqi Qi, Wen Liu, Zibo Zhao, Zhibin Wang, Bin Fu, Yong liu, Gang Yu
This paper presents Paint3D, a novel coarse-to-fine generative framework that is capable of producing high-resolution, lighting-less, and diverse 2K UV texture maps for untextured 3D meshes conditioned on text or image inputs.
1 code implementation • 19 Dec 2023 • Yanqi Ge, Qiang Nie, Ye Huang, Yong liu, Chengjie Wang, Feng Zheng, Wen Li, Lixin Duan
By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem.
1 code implementation • 19 Dec 2023 • Chun-Mei Feng, Yang Bai, Tao Luo, Zhen Li, Salman Khan, WangMeng Zuo, Xinxing Xu, Rick Siow Mong Goh, Yong liu
By feeding the retrieved image and question to the VQA model, one can find the images inconsistent with relative caption when the answer by VQA is inconsistent with the answer in the QA pair.
no code implementations • 17 Dec 2023 • Jingyang Xiang, Zhuangzhi Chen, Jianbiao Mei, Siqi Li, Jun Chen, Yong liu
In this paper, we propose to mitigate this gap by learning consistent representation for soft filter pruning, dubbed as CR-SFP.
1 code implementation • 12 Dec 2023 • Jiangning Zhang, Xuhai Chen, Yabiao Wang, Chengjie Wang, Yong liu, Xiangtai Li, Ming-Hsuan Yang, DaCheng Tao
Following this spirit, this paper explores plain ViT architecture for MUAD.
1 code implementation • 12 Dec 2023 • Jingyang Xiang, Siqi Li, JunHao Chen, Zhuangzhi Chen, Tianxin Huang, Linpeng Peng, Yong liu
Meanwhile, a sparsity strategy that gradually increases the percentage of N:M weight blocks is applied, which allows the network to heal from the pruning-induced damage progressively.
1 code implementation • 10 Dec 2023 • Jianbiao Mei, Yu Yang, Mengmeng Wang, Junyu Zhu, Xiangrui Zhao, Jongwon Ra, Laijian Li, Yong liu
Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving.
no code implementations • 10 Dec 2023 • Ruyue Liu, Rong Yin, Yong liu, Weiping Wang
Graph Comparative Learning (GCL) is a self-supervised method that combines the advantages of Graph Convolutional Networks (GCNs) and comparative learning, making it promising for learning node representations.
1 code implementation • 7 Dec 2023 • Xin Li, Yeqi Bai, Pinlong Cai, Licheng Wen, Daocheng Fu, Bo Zhang, Xuemeng Yang, Xinyu Cai, Tao Ma, Jianfei Guo, Xing Gao, Min Dou, Yikang Li, Botian Shi, Yong liu, Liang He, Yu Qiao
This paper explores the emerging knowledge-driven autonomous driving technologies.
1 code implementation • 7 Dec 2023 • Yong liu, Sule Bai, Guanbin Li, Yitong Wang, Yansong Tang
We attribute this to the in-vocabulary embedding and domain-biased CLIP prediction.
1 code implementation • 4 Dec 2023 • Yong liu, Cairong Zhang, Yitong Wang, Jiahao Wang, Yujiu Yang, Yansong Tang
This paper aims to achieve universal segmentation of arbitrary semantic level.
Ranked #1 on Referring Expression Segmentation on RefCOCOg-test (using extra training data)
1 code implementation • 28 Nov 2023 • Yicheng Xiao, Zhuoyan Luo, Yong liu, Yue Ma, Hengwei Bian, Yatai Ji, Yujiu Yang, Xiu Li
Video Moment Retrieval (MR) and Highlight Detection (HD) have attracted significant attention due to the growing demand for video analysis.
Ranked #1 on Highlight Detection on YouTube Highlights
no code implementations • 8 Nov 2023 • Huayi Tang, Yong liu
In this paper, we develop data-dependent and algorithm-dependent generalization bounds for transductive learning algorithms in the context of information theory for the first time.
1 code implementation • 6 Nov 2023 • Mingjia Yin, Hao Wang, Xiang Xu, Likang Wu, Sirui Zhao, Wei Guo, Yong liu, Ruiming Tang, Defu Lian, Enhong Chen
To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems.
1 code implementation • 5 Nov 2023 • Jiangning Zhang, Haoyang He, Xuhai Chen, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong liu
Large Multimodal Model (LMM) GPT-4V(ision) endows GPT-4 with visual grounding capabilities, making it possible to handle certain tasks through the Visual Question Answering (VQA) paradigm.
no code implementations • 2 Nov 2023 • Yulan Hu, Sheng Ouyang, Zhirui Yang, Yong liu
VIGraph strictly adheres to the concept of imbalance when constructing imbalanced graphs and innovatively leverages the variational inference (VI) ability of Variational GAE to generate nodes for minority classes.
no code implementations • 1 Nov 2023 • Xuhai Chen, Jiangning Zhang, Guanzhong Tian, Haoyang He, Wuhao Zhang, Yabiao Wang, Chengjie Wang, Yong liu
This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects.
1 code implementation • 31 Oct 2023 • Sunhao Dai, Yuqi Zhou, Liang Pang, Weihao Liu, Xiaolin Hu, Yong liu, Xiao Zhang, Gang Wang, Jun Xu
We refer to this category of biases in neural retrieval models towards the LLM-generated text as the \textbf{source bias}.
no code implementations • 25 Oct 2023 • Yonghao Wu, Zheng Li, Jie M. Zhang, Yong liu
With the growing interest on Large Language Models (LLMs) for fault localization and program repair, ensuring the integrity and generalizability of the LLM-based methods becomes paramount.
1 code implementation • 24 Oct 2023 • Fu-Ya Luo, Shu-Lin Liu, Yi-Jun Cao, Kai-Fu Yang, Chang-Yong Xie, Yong liu, Yong-Jie Li
Extensive experiments illustrate that the proposed FoalGAN is not only effective for appearance learning of small objects, but also outperforms other image translation methods in terms of semantic preservation and edge consistency for the NTIR2DC task.
no code implementations • 23 Oct 2023 • Yulan Hu, Sheng Ouyang, Jingyu Liu, Ge Chen, Zhirui Yang, Junchen Wan, Fuzheng Zhang, Zhongyuan Wang, Yong liu
Thus, we propose GraphRank, a simple yet efficient graph contrastive learning method that addresses the problem of false negative samples by redefining the concept of negative samples to a certain extent, thereby avoiding the issue of false negative samples.
no code implementations • 20 Oct 2023 • Ruifeng Ren, Yong liu
To the best of our knowledge, our work is the first to provide the understanding of ICL from the perspective of contrastive learning and has the potential to facilitate future model design by referring to related works on contrastive learning.
no code implementations • 18 Oct 2023 • Manna Dai, Yang Jiang, Feng Yang, Joyjit Chattoraj, Yingzhi Xia, Xinxing Xu, Weijiang Zhao, My Ha Dao, Yong liu
Metasurfaces have widespread applications in fifth-generation (5G) microwave communication.
no code implementations • 17 Oct 2023 • Yulan Hu, Zhirui Yang, Sheng Ouyang, Junchen Wan, Fuzheng Zhang, Zhongyuan Wang, Yong liu
In this study, we aim to explore the problem of generative SSL in the context of heterogeneous graph learning (HGL).
1 code implementation • 17 Oct 2023 • Wei Yao, Zhanke Zhou, Zhicong Li, Bo Han, Yong liu
To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem.
no code implementations • 11 Oct 2023 • Yizhi Wang, Shichuan Xue, Yaxuan Wang, Jiangfang Ding, Weixu Shi, Dongyang Wang, Yong liu, Yingwen Liu, Xiang Fu, Guangyao Huang, Anqi Huang, Mingtang Deng, Junjie Wu
Our work opens up a vista of utilizing QNG in photonics to implement practical near-term quantum applications.
1 code implementation • 10 Oct 2023 • Jingyang Xiang, Siqi Li, Jun Chen, Shipeng Bai, Yukai Ma, Guang Dai, Yong liu
To overcome them, this paper proposes a novel \emph{\textbf{S}oft \textbf{U}niform \textbf{B}lock \textbf{P}runing} (SUBP) approach to train a uniform 1$\times$N sparse structured network from scratch.
4 code implementations • 10 Oct 2023 • Yong liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, Mingsheng Long
These forecasters leverage Transformers to model the global dependencies over temporal tokens of time series, with each token formed by multiple variates of the same timestamp.
1 code implementation • 9 Oct 2023 • Yang Bai, Xinxing Xu, Yong liu, Salman Khan, Fahad Khan, WangMeng Zuo, Rick Siow Mong Goh, Chun-Mei Feng
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption.
Ranked #1 on Image Retrieval on CIRR
no code implementations • 6 Oct 2023 • Jingyu Liu, Huayi Tang, Yong liu
Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive pairs and separating negative ones.
no code implementations • 1 Oct 2023 • Yizhi Wang, Shichuan Xue, Yaxuan Wang, Yong liu, Jiangfang Ding, Weixu Shi, Dongyang Wang, Yingwen Liu, Xiang Fu, Guangyao Huang, Anqi Huang, Mingtang Deng, Junjie Wu
Quantum Generative Adversarial Networks (QGANs), an intersection of quantum computing and machine learning, have attracted widespread attention due to their potential advantages over classical analogs.
no code implementations • 28 Sep 2023 • Jialin Li, WeiFu Fu, Yuhuan Lin, Qiang Nie, Yong liu
Query-based object detectors have made significant advancements since the publication of DETR.
1 code implementation • NeurIPS 2023 • Jiaqi Liu, Guoyang Xie, Ruitao Chen, Xinpeng Li, Jinbao Wang, Yong liu, Chengjie Wang, Feng Zheng
High-precision point cloud anomaly detection is the gold standard for identifying the defects of advancing machining and precision manufacturing.
1 code implementation • 13 Sep 2023 • Yingjie Zhao, Yong liu, Zhiping Xu
Predicting potential risks associated with the fatigue of key structural components is crucial in engineering design.
no code implementations • 9 Sep 2023 • Yuanguo Lin, Hong Chen, Wei Xia, Fan Lin, Zongyue Wang, Yong liu
With the increasing complexity and diversity of educational data, Deep Learning techniques have shown significant advantages in addressing the challenges associated with analyzing and modeling this data.
no code implementations • 31 Aug 2023 • Chenyao Jiang, Shiyao Zhai, Hengrui Song, Yuqing Ma, Yachen Fan, Yancheng Fang, Dongmei Yu, Canyang Zhang, Sanyang Han, Runming Wang, Yong liu, Jianbo Li, Peiwu Qin
The best result for YOLOXs model with tiling strategy is 72. 3 mAP. 5, while the best result without tiling strategy is 71. 2.
no code implementations • 30 Aug 2023 • WeiFu Fu, Qiang Nie, Jialin Li, Yuhuan Lin, Kai Wu, Jian Li, Yabiao Wang, Yong liu, Chengjie Wang
In this paper, we highlight the significance of exploiting the intra-domain information between the labeled target data and unlabeled target data.
1 code implementation • 30 Aug 2023 • Hengchang Hu, Wei Guo, Yong liu, Min-Yen Kan
We propose a graph-based approach (named MMSR) to fuse modality features in an adaptive order, enabling each modality to prioritize either its inherent sequential nature or its interplay with other modalities.
1 code implementation • 28 Aug 2023 • Junyu Zhu, Lina Liu, Yu Tang, Feng Wen, Wanlong Li, Yong liu
In this paper, we present a novel semi-supervised framework for visual BEV semantic segmentation to boost performance by exploiting unlabeled images during the training.
Autonomous Vehicles Bird's-Eye View Semantic Segmentation +2
no code implementations • ICCV 2023 • Teli Ma, Mengmeng Wang, Jimin Xiao, Huifeng Wu, Yong liu
In this paper, we forsake the conventional Siamese paradigm and propose a novel single-branch framework, SyncTrack, synchronizing the feature extracting and matching to avoid forwarding encoder twice for template and search region as well as introducing extra parameters of matching network.
no code implementations • 23 Aug 2023 • Donghao Zhou, Jialin Li, Jinpeng Li, Jiancheng Huang, Qiang Nie, Yong liu, Bin-Bin Gao, Qiong Wang, Pheng-Ann Heng, Guangyong Chen
Large-scale well-annotated datasets are of great importance for training an effective object detector.
no code implementations • 21 Aug 2023 • Jun Chen, Haishan Ye, Mengmeng Wang, Tianxin Huang, Guang Dai, Ivor W. Tsang, Yong liu
This paper proposes a decentralized Riemannian conjugate gradient descent (DRCGD) method that aims at minimizing a global function over the Stiefel manifold.
1 code implementation • ICCV 2023 • Jiazheng Xing, Mengmeng Wang, Yudi Ruan, Bofan Chen, Yaowei Guo, Boyu Mu, Guang Dai, Jingdong Wang, Yong liu
Class prototype construction and matching are core aspects of few-shot action recognition.
2 code implementations • 17 Aug 2023 • Jiahao Zhang, Haiyang Zhang, Dongmei Zhang, Yong liu, Shen Huang
This approach models the multi-hop retrieval process in an end-to-end manner by jointly optimizing an encoder and two classification heads across all hops.
Ranked #1 on Question Answering on HotpotQA
no code implementations • 15 Aug 2023 • Xunyu Zhu, Jian Li, Yong liu, Can Ma, Weiping Wang
As these challenges become increasingly pertinent, the field of model compression has emerged as a pivotal research area to alleviate these limitations.
no code implementations • ICCV 2023 • Shipeng Bai, Jun Chen, Xintian Shen, Yixuan Qian, Yong liu
Therefore, a few data-free methods are proposed to address this problem, but they perform data-free pruning and quantization separately, which does not explore the complementarity of pruning and quantization.
1 code implementation • ICCV 2023 • Chun-Mei Feng, Kai Yu, Yong liu, Salman Khan, WangMeng Zuo
In this paper, we focus on a particular setting of learning adaptive prompts on the fly for each test sample from an unseen new domain, which is known as test-time prompt tuning (TPT).
1 code implementation • 5 Aug 2023 • Yong liu, Hang Dong, Boyang Liang, Songwei Liu, Qingji Dong, Kai Chen, Fangmin Chen, Lean Fu, Fei Wang
Since the high resolution of intermediate features in SISR models increases memory and computational requirements, efficient SISR transformers are more favored.
1 code implementation • 3 Aug 2023 • Qianwen Meng, Hangwei Qian, Yong liu, Yonghui Xu, Zhiqi Shen, Lizhen Cui
However, there is a lack of systematic analysis of unsupervised representation learning approaches for time series.
no code implementations • 3 Aug 2023 • Jiazheng Xing, Mengmeng Wang, Xiaojun Hou, Guang Dai, Jingdong Wang, Yong liu
The adapters we design can combine information from video-text multimodal sources for task-oriented spatiotemporal modeling, which is fast, efficient, and has low training costs.
no code implementations • 25 Jul 2023 • Shaojie Li, Yong liu
Gradient clipping is a commonly used technique to stabilize the training process of neural networks.
1 code implementation • 14 Jul 2023 • Chen Qian, Huayi Tang, Zhirui Yang, Hong Liang, Yong liu
Molecular property prediction has gained significant attention due to its transformative potential in multiple scientific disciplines.
no code implementations • 13 Jul 2023 • Kai Su, Yoichi Tomioka, Qiangfu Zhao, Yong liu
In the realm of Tiny AI, we introduce ``You Only Look at Interested Cells" (YOLIC), an efficient method for object localization and classification on edge devices.
no code implementations • 2 Jul 2023 • Jun Chen, Shipeng Bai, Tianxin Huang, Mengmeng Wang, Guanzhong Tian, Yong liu
In this paper, we propose a data-free mixed-precision compensation (DF-MPC) method to recover the performance of an ultra-low precision quantized model without any data and fine-tuning process.
1 code implementation • 27 Jun 2023 • Jianbiao Mei, Yu Yang, Mengmeng Wang, Xiaojun Hou, Laijian Li, Yong liu
Firstly, we propose a non-learning Sparse Instance Proposal (SIP) module with the ``sampling-shifting-grouping" scheme to directly group thing points into instances from the raw point cloud efficiently.
1 code implementation • 27 Jun 2023 • Jianbiao Mei, Yu Yang, Mengmeng Wang, Tianxin Huang, Xuemeng Yang, Yong liu
However, how to effectively exploit the relationships between the semantic context in semantic segmentation and geometric structure in scene completion remains under exploration.
1 code implementation • 16 Jun 2023 • Kexin Zhang, Qingsong Wen, Chaoli Zhang, Rongyao Cai, Ming Jin, Yong liu, James Zhang, Yuxuan Liang, Guansong Pang, Dongjin Song, Shirui Pan
To fill this gap, we review current state-of-the-art SSL methods for time series data in this article.
1 code implementation • 9 Jun 2023 • Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Hao Zhang, Yong liu, Chuhan Wu, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, Weinan Zhang
In this paper, we conduct a comprehensive survey on this research direction from the perspective of the whole pipeline in real-world recommender systems.
1 code implementation • 8 Jun 2023 • Juntao Jiang, Xiyu Chen, Guanzhong Tian, Yong liu
Deep neural networks have been widely used in medical image analysis and medical image segmentation is one of the most important tasks.
1 code implementation • NeurIPS 2023 • Yong liu, Chenyu Li, Jianmin Wang, Mingsheng Long
While previous models suffer from complicated series variations induced by changing temporal distribution, we tackle non-stationary time series with modern Koopman theory that fundamentally considers the underlying time-variant dynamics.
1 code implementation • NeurIPS 2023 • Zhuoyan Luo, Yicheng Xiao, Yong liu, Shuyan Li, Yitong Wang, Yansong Tang, Xiu Li, Yujiu Yang
To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for unified temporal modeling and cross-modal alignment.
Ranked #2 on Referring Expression Segmentation on A2D Sentences (using extra training data)
no code implementations • ICCV 2023 • Xintian Shen, Jiangning Zhang, Jun Chen, Shipeng Bai, Yue Han, Yabiao Wang, Chengjie Wang, Yong liu
To address this issue, we propose a novel Global-aware Kernel Network (GKNet) to harmonize local regions with comprehensive consideration of long-distance background references.
Ranked #5 on Image Harmonization on iHarmony4
no code implementations • 16 May 2023 • Mengmeng Wang, Teli Ma, Xingxing Zuo, Jiajun Lv, Yong liu
Additionally, considering the sparsity characteristics of the point clouds, we design a lateral correlation pyramid structure for the encoder to keep as many points as possible by integrating hierarchical correlated features.
no code implementations • 14 May 2023 • Huayi Tang, Yong liu
After that, we provide high probability bounds of generalization gap for popular GNNs.
no code implementations • 10 May 2023 • Zhuofei Huang, Jianlin Liu, Shang Xu, Ying Chen, Yong liu
Multi-view stereo depth estimation based on cost volume usually works better than self-supervised monocular depth estimation except for moving objects and low-textured surfaces.
no code implementations • 4 May 2023 • Chao Xu, Shaoting Zhu, Junwei Zhu, Tianxin Huang, Jiangning Zhang, Ying Tai, Yong liu
More specifically, given a textured face as the source and the rendered face projected from the desired 3DMM coefficients as the target, our proposed Texture-Geometry-aware Diffusion Model decomposes the complex transfer problem into multi-conditional denoising process, where a Texture Attention-based module accurately models the correspondences between appearance and geometry cues contained in source and target conditions, and incorporate extra implicit information for high-fidelity talking face generation.
no code implementations • CVPR 2023 • Chao Xu, Junwei Zhu, Jiangning Zhang, Yue Han, Wenqing Chu, Ying Tai, Chengjie Wang, Zhifeng Xie, Yong liu
Specifically, we supplement the emotion style in text prompts and use an Aligned Multi-modal Emotion encoder to embed the text, image, and audio emotion modality into a unified space, which inherits rich semantic prior from CLIP.
1 code implementation • 17 Apr 2023 • Jianlin Liu, Qiang Nie, Yong liu, Chengjie Wang
We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer.
2 code implementations • 12 Apr 2023 • Jiahao Wang, Songyang Zhang, Yong liu, Taiqiang Wu, Yujiu Yang, Xihui Liu, Kai Chen, Ping Luo, Dahua Lin
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
no code implementations • 8 Apr 2023 • Meng Wang, Tian Lin, Lianyu Wang, Aidi Lin, Ke Zou, Xinxing Xu, Yi Zhou, Yuanyuan Peng, Qingquan Meng, Yiming Qian, Guoyao Deng, Zhiqun Wu, Junhong Chen, Jianhong Lin, Mingzhi Zhang, Weifang Zhu, Changqing Zhang, Daoqiang Zhang, Rick Siow Mong Goh, Yong liu, Chi Pui Pang, Xinjian Chen, Haoyu Chen, Huazhu Fu
Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies.
1 code implementation • CVPR 2023 • Xuhai Chen, Jiangning Zhang, Chao Xu, Yabiao Wang, Chengjie Wang, Yong liu
Most of the existing blind image Super-Resolution (SR) methods assume that the blur kernels are space-invariant.
no code implementations • 6 Apr 2023 • Xunyu Zhu, Jian Li, Yong liu, Weiping Wang
Neural Architectures Search (NAS) becomes more and more popular over these years.
1 code implementation • CVPR 2023 • Chun-Mei Feng, Bangjun Li, Xinxing Xu, Yong liu, Huazhu Fu, WangMeng Zuo
Federated Magnetic Resonance Imaging (MRI) reconstruction enables multiple hospitals to collaborate distributedly without aggregating local data, thereby protecting patient privacy.
no code implementations • 23 Mar 2023 • Meng Wang, Lianyu Wang, Xinxing Xu, Ke Zou, Yiming Qian, Rick Siow Mong Goh, Yong liu, Huazhu Fu
Our TWEU employs an evidential deep layer to produce the uncertainty score with the DR staging results for client reliability evaluation.
1 code implementation • ICCV 2023 • Kunyang Han, Yong liu, Jun Hao Liew, Henghui Ding, Yunchao Wei, Jiajun Liu, Yitong Wang, Yansong Tang, Yujiu Yang, Jiashi Feng, Yao Zhao
Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS).
Knowledge Distillation Open Vocabulary Semantic Segmentation +4
1 code implementation • ICCV 2023 • Zizhang Li, Xiaoyang Lyu, Yuanyuan Ding, Mengmeng Wang, Yiyi Liao, Yong liu
Recently, neural implicit surfaces have become popular for multi-view reconstruction.
no code implementations • 14 Mar 2023 • Zhihao Chen, Yang Zhou, Anh Tran, Junting Zhao, Liang Wan, Gideon Ooi, Lionel Cheng, Choon Hua Thng, Xinxing Xu, Yong liu, Huazhu Fu
To enable MedRPG to locate nuanced medical findings with better region-phrase correspondences, we further propose Tri-attention Context contrastive alignment (TaCo).
1 code implementation • 13 Mar 2023 • Chencan Fu, Lin Li, Linpeng Peng, Yukai Ma, Xiangrui Zhao, Yong liu
Place recognition is a challenging yet crucial task in robotics.
1 code implementation • 28 Feb 2023 • Lin Li, Wendong Ding, Yongkun Wen, Yufei Liang, Yong liu, Guowei Wan
For overlap detection, a cross-attention module is applied for interacting contextual information of input point clouds, followed by a classification head to estimate the overlapping region.
no code implementations • 16 Feb 2023 • Yunliang Jiang, Lili Yan, Xiongtao Zhang, Yong liu, Danfeng Sun
One-shot image generation (OSG) with generative adversarial networks that learn from the internal patches of a given image has attracted world wide attention.
no code implementations • 16 Feb 2023 • Xiongtao Zhang, Zezong Yin, Yunliang Jiang, Yizhang Jiang, Danfeng Sun, Yong liu
High-order Takagi-Sugeno-Kang (TSK) fuzzy classifiers possess powerful classification performance yet have fewer fuzzy rules, but always be impaired by its exponential growth training time and poorer interpretability owing to High-order polynomial used in consequent part of fuzzy rule, while Low-order TSK fuzzy classifiers run quickly with high interpretability, however they usually require more fuzzy rules and perform relatively not very well.
1 code implementation • 14 Feb 2023 • Shanqi Liu, Yujing Hu, Runze Wu, Dong Xing, Yu Xiong, Changjie Fan, Kun Kuang, Yong liu
We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios.
1 code implementation • 11 Feb 2023 • Xunyu Zhu, Jian Li, Yong liu, Weiping Wang
It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.
no code implementations • 11 Feb 2023 • Xunyu Zhu, Jian Li, Yong liu, Weiping Wang
Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.
no code implementations • 7 Feb 2023 • Jun Chen, Hanwen Chen, Mengmeng Wang, Guang Dai, Ivor W. Tsang, Yong liu
By introducing a partial differential equation on metrics, i. e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the $L^2$-norm perturbation.
no code implementations • 2 Feb 2023 • Tong Zhang, Yong liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui
HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses.
2 code implementations • 31 Jan 2023 • Guoyang Xie, Jinbao Wang, Jiaqi Liu, Jiayi Lyu, Yong liu, Chengjie Wang, Feng Zheng, Yaochu Jin
We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-world applications.
no code implementations • 30 Jan 2023 • Meng Wang, Kai Yu, Chun-Mei Feng, Yiming Qian, Ke Zou, Lianyu Wang, Rick Siow Mong Goh, Yong liu, Huazhu Fu
To the best of our knowledge, our proposed RFedDis is the first work to develop an FL approach based on evidential uncertainty combined with feature disentangling, which enhances the performance and reliability of FL in non-IID domain features.
no code implementations • 20 Jan 2023 • Junyu Zhu, Lina Liu, Yong liu, Wanlong Li, Feng Wen, Hongbo Zhang
The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods.
no code implementations • 19 Jan 2023 • Jiazheng Xing, Mengmeng Wang, Yong liu, Boyu Mu
In this paper, we propose SloshNet, a new framework that revisits the spatial and temporal modeling for few-shot action recognition in a finer manner.
no code implementations • 17 Jan 2023 • Haoxin Chen, Mengmeng Wang, Yong liu
The locality of lane representation is the ability to modify lanes locally which can simplify parameter optimization.
1 code implementation • 3 Jan 2023 • Yue Han, Jiangning Zhang, Zhucun Xue, Chao Xu, Xintian Shen, Yabiao Wang, Chengjie Wang, Yong liu, Xiangtai Li
In this work, we explore a simple yet unified solution for FSIS as well as its incremental variants, and introduce a new framework named Reference Twice (RefT) to fully explore the relationship between support/query features based on a Transformer-like framework.
no code implementations • CVPR 2023 • Jiahao Wang, Songyang Zhang, Yong liu, Taiqiang Wu, Yujiu Yang, Xihui Liu, Kai Chen, Ping Luo, Dahua Lin
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
no code implementations • CVPR 2023 • Tianxin Huang, Zhonggan Ding, Jiangning Zhang, Ying Tai, Zhenyu Zhang, Mingang Chen, Chengjie Wang, Yong liu
Specifically, we use the contrastive constraint to help CALoss learn a representation space with shape similarity, while we introduce the adversarial strategy to help CALoss mine differences between reconstructed results and ground truths.
no code implementations • CVPR 2023 • Jiechao Yang, Yong liu, Hongteng Xu
To address these issues, we propose a hierarchical optimal transport metric called HOTNN for measuring the similarity of different networks.
1 code implementation • CVPR 2023 • Pengwei Tang, Wei Yao, Zhicong Li, Yong liu
We randomly initialize a dense neural network and find appropriate binary masks for the weights to obtain fair sparse subnetworks without any weight training.
1 code implementation • ICCV 2023 • Chi Zhang, Zhang Xiaoman, Ekanut Sotthiwat, Yanyu Xu, Ping Liu, Liangli Zhen, Yong liu
Federated learning has gained recognitions as a secure approach for safeguarding local private data in collaborative learning.
3 code implementations • 1 Jan 2023 • Ke Zou, Yidi Chen, Ling Huang, Xuedong Yuan, Xiaojing Shen, Meng Wang, Rick Siow Mong Goh, Yong liu, Huazhu Fu
DEviS not only enhances the calibration and robustness of baseline segmentation accuracy but also provides high-efficiency uncertainty estimation for reliable predictions.
no code implementations • 27 Dec 2022 • Zehua Sun, Yonghui Xu, Yong liu, wei he, Lanju Kong, Fangzhao Wu, Yali Jiang, Lizhen Cui
Federated learning has recently been applied to recommendation systems to protect user privacy.
no code implementations • 9 Dec 2022 • Xinzhe Ni, Yong liu, Hao Wen, Yatai Ji, Jing Xiao, Yujiu Yang
Then in the visual flow, visual prototypes are computed by a Temporal-Relational CrossTransformer (TRX) module for example.
no code implementations • 3 Dec 2022 • Tianwei Lin, Honglin Lin, Fu Li, Dongliang He, Wenhao Wu, Meiling Wang, Xin Li, Yong liu
Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair.
1 code implementation • 2 Dec 2022 • Qianwen Meng, Hangwei Qian, Yong liu, Lizhen Cui, Yonghui Xu, Zhiqi Shen
Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting.
no code implementations • 1 Dec 2022 • Meng Wang, Kai Yu, Chun-Mei Feng, Ke Zou, Yanyu Xu, Qingquan Meng, Rick Siow Mong Goh, Yong liu, Huazhu Fu
Specifically, aiming at improving the model's ability to learn the complex pathological features of retinal edema lesions in OCT images, we develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module of our newly designed.
1 code implementation • 5 Nov 2022 • Xin Zhou, Jinglong Wang, Yong liu, Xingyu Wu, Zhiqi Shen, Cyril Leung
Providing accurate estimated time of package delivery on users' purchasing pages for e-commerce platforms is of great importance to their purchasing decisions and post-purchase experiences.
1 code implementation • 11 Oct 2022 • Yong liu, Ran Yu, Jiahao Wang, Xinyuan Zhao, Yitong Wang, Yansong Tang, Yujiu Yang
Besides, we empirically find low frequency feature should be enhanced in encoder (backbone) while high frequency for decoder (segmentation head).
no code implementations • 6 Oct 2022 • Chen Li, Xiaoyu Wang, Tongyu Zong, Houwei Cao, Yong liu
Edge caching plays an increasingly important role in boosting user content retrieval performance while reducing redundant network traffic.
3 code implementations • 5 Oct 2022 • Haixu Wu, Tengge Hu, Yong liu, Hang Zhou, Jianmin Wang, Mingsheng Long
TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block.
no code implementations • 30 Sep 2022 • Li Zhang, Yong liu, Shaoteng Liu, Tianshu Yang, Yexin Wang, Xinpeng Zhang, Hanzhou Wu
Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing.
no code implementations • 29 Sep 2022 • Yunliang Jiang, Chenyang Gu, Zhenfeng Xue, Xiongtao Zhang, Yong liu
As a special case of common object removal, image person removal is playing an increasingly important role in social media and criminal investigation domains.
1 code implementation • 25 Sep 2022 • Xiaofeng Lei, Shaohua Li, Xinxing Xu, Huazhu Fu, Yong liu, Yih-Chung Tham, Yangqin Feng, Mingrui Tan, Yanyu Xu, Jocelyn Hui Lin Goh, Rick Siow Mong Goh, Ching-Yu Cheng
Therefore, localization has its unique challenges different from segmentation or detection.
no code implementations • 20 Sep 2022 • Dihe Huang, Ying Chen, Yikang Ding, Jinli Liao, Jianlin Liu, Kai Wu, Qiang Nie, Yong liu, Chengjie Wang, Zhiheng Li
In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation.
no code implementations • 13 Sep 2022 • Zhenfeng Xue, Jiandang Yang, Jie Ren, Yong liu
This method can be viewed as a hybrid of exemplar-based and learning-based method, and it decouples the colorization process and learning process so as to generate various color styles for the same gray image.
no code implementations • 31 Aug 2022 • Jianlin Liu, Zhuofei Huang, Dihe Huang, Shang Xu, Ying Chen, Yong liu
3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision.
1 code implementation • 29 Aug 2022 • Yifeng Zhou, Chuming Lin, Donghao Luo, Yong liu, Ying Tai, Chengjie Wang, Mingang Chen
Although some Unsupervised Degradation Prediction (UDP) methods are proposed to bypass this problem, the \textit{inconsistency} between degradation embedding and SR feature is still challenging.
no code implementations • 21 Aug 2022 • Yongwei Wang, Yong liu, Zhiqi Shen
However, there still lack efforts to evaluate the robustness of such CF systems in deployment.
no code implementations • Knowledge-Based Systems 2022 • Changan Yi, Haotian Chen, Yonghui Xu, Yong liu, Lei Jiang, Haishu Tan
Accordingly, ATPL will use the pseudo-labeled information to improve the adversarial training process, which can guarantee the feature transferability by generating adversarial data to fill in the domain gap.
1 code implementation • 3 Aug 2022 • Xiangrui Zhao, Sheng Yang, Tianxin Huang, Jun Chen, Teng Ma, Mingyang Li, Yong liu
To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.
no code implementations • 31 Jul 2022 • Guangyao Zhai, Yu Zheng, Ziwei Xu, Xin Kong, Yong liu, Benjamin Busam, Yi Ren, Nassir Navab, Zhengyou Zhang
In this paper, we introduce DA$^2$, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects.
1 code implementation • 22 Jul 2022 • Xin Zhou, Donghui Lin, Yong liu, Chunyan Miao
Specifically, these models usually aggregate all layer embeddings for node updating and achieve their best recommendation performance within a few layers because of over-smoothing.
1 code implementation • CVPR 2023 • Dihe Huang, Ying Chen, Shang Xu, Yong liu, Wenlong Wu, Yikang Ding, Chengjie Wang, Fan Tang
The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance.
1 code implementation • 17 Jul 2022 • Zizhang Li, Mengmeng Wang, Huaijin Pi, Kechun Xu, Jianbiao Mei, Yong liu
However, the redundant parameters within the network structure can cause a large model size when scaling up for desirable performance.
Ranked #4 on Video Reconstruction on UVG
1 code implementation • 16 Jul 2022 • Yong liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, Yujiu Yang
However, they mainly focus on better matching between the current frame and the memory frames without explicitly paying attention to the quality of the memory.
Ranked #11 on Semi-Supervised Video Object Segmentation on DAVIS 2016 (using extra training data)
2 code implementations • 13 Jul 2022 • Xin Zhou, HongYu Zhou, Yong liu, Zhiwei Zeng, Chunyan Miao, Pengwei Wang, Yuan You, Feijun Jiang
Besides the user-item interaction graph, existing state-of-the-art methods usually use auxiliary graphs (e. g., user-user or item-item relation graph) to augment the learned representations of users and/or items.
no code implementations • 29 Jun 2022 • Yinan Zhang, Boyang Li, Yong liu, You Yuan, Chunyan Miao
Multi-shot CRS is designed to make recommendations multiple times until the user either accepts the recommendation or leaves at the end of their patience.
1 code implementation • 19 Jun 2022 • Jiangning Zhang, Xiangtai Li, Yabiao Wang, Chengjie Wang, Yibo Yang, Yong liu, DaCheng Tao
Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derives that both have consistent mathematical formulation.
no code implementations • 6 Jun 2022 • Yuzhe Li, Yong liu, Bo Li, Weiping Wang, Nan Liu
In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.
no code implementations • 30 May 2022 • Yixin Zhang, Yong liu, Yonghui Xu, Hao Xiong, Chenyi Lei, wei he, Lizhen Cui, Chunyan Miao
Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data.
1 code implementation • 28 May 2022 • Yong liu, Haixu Wu, Jianmin Wang, Mingsheng Long
However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time.
1 code implementation • 25 May 2022 • Yimin Ou, Rui Yang, Lufan Ma, Yong liu, Jiangpeng Yan, Shang Xu, Chengjie Wang, Xiu Li
Existing instance segmentation methods have achieved impressive performance but still suffer from a common dilemma: redundant representations (e. g., multiple boxes, grids, and anchor points) are inferred for one instance, which leads to multiple duplicated predictions.
1 code implementation • 1 May 2022 • Jian Li, Yong liu, Yingying Zhang
Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization.
no code implementations • 30 Apr 2022 • Shaojie Li, Sheng Ouyang, Yong liu
The theoretical analysis of spectral clustering mainly focuses on consistency, while there is relatively little research on its generalization performance.
no code implementations • 22 Apr 2022 • Yilin Kang, Yong liu, Jian Li, Weiping Wang
In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.
no code implementations • 11 Apr 2022 • Yilin Kang, Yong liu, Jian Li, Weiping Wang
To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.
1 code implementation • CVPR 2022 • Xiuchao Sui, Shaohua Li, Xue Geng, Yan Wu, Xinxing Xu, Yong liu, Rick Goh, Hongyuan Zhu
This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images.
Ranked #9 on Optical Flow Estimation on KITTI 2015 (train)
no code implementations • CVPR 2022 • Chao Xu, Jiangning Zhang, Miao Hua, Qian He, Zili Yi, Yong liu
This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction.
2 code implementations • CVPR 2022 • Yong liu, Siqi Mai, Xiangning Chen, Cho-Jui Hsieh, Yang You
Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated significant performance boosts on training large-scale models such as vision transformers.
1 code implementation • CVPR 2022 • Fan Yang, Kai Wu, Shuyi Zhang, Guannan Jiang, Yong liu, Feng Zheng, Wei zhang, Chengjie Wang, Long Zeng
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization.
1 code implementation • 1 Mar 2022 • Yufei Liang, Jiangning Zhang, Shiwei Zhao, Runze Wu, Yong liu, Shuwen Pan
Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based methods are rarely mentioned for the poor reconstruction ability and low performance.
Ranked #39 on Anomaly Detection on MVTec AD
1 code implementation • 18 Feb 2022 • Ying Chen, Dihe Huang, Shang Xu, Jianlin Liu, Yong liu
Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important.
1 code implementation • 14 Feb 2022 • Xi Jiang, Guoyang Xie, Jinbao Wang, Yong liu, Chengjie Wang, Feng Zheng, Yaochu Jin
In this survey, we are the first one to provide a comprehensive review of visual sensory AD and category into three levels according to the form of anomalies.
no code implementations • 16 Jan 2022 • Fan Wang, Chaofan Zhang, Fulin Tang, Hongkui Jiang, Yihong Wu, Yong liu
In this paper, we present a novel lightweight object-level mapping and localization method with high accuracy and robustness.
no code implementations • 12 Jan 2022 • Jiangning Zhang, Chao Xu, Jian Li, Yue Han, Yabiao Wang, Ying Tai, Yong liu
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.
2 code implementations • 7 Jan 2022 • YiWei Chen, Gongxin Yao, Yong liu, Hongye Su, Xiaomin Hu, Yu Pan
Photon-efficient imaging with the single-photon light detection and ranging (LiDAR) captures the three-dimensional (3D) structure of a scene by only a few detected signal photons per pixel.
2 code implementations • 5 Jan 2022 • Gongxin Yao, YiWei Chen, Yong liu, Xiaomin Hu, Yu Pan
Single-photon light detection and ranging (LiDAR) has been widely applied to 3D imaging in challenging scenarios.
no code implementations • CVPR 2022 • Huayi Tang, Yong liu
However, we observe that learning from data with more views is not guaranteed to achieve better clustering performance than from data with fewer views.
no code implementations • 21 Dec 2021 • Jun Chen, Yuang Liu, Xiangrui Zhao, Mengmeng Wang, Yong liu
As a result, we prove that, if initial metrics have an $L^2$-norm perturbation which deviates from the Hyperbolic metric on the Poincar\'e ball, the scaled Ricci-DeTurck flow of such metrics smoothly and exponentially converges to the Hyperbolic metric.
no code implementations • 20 Dec 2021 • Xianfang Zeng, Jiangning Zhang, Liang Liu, Guangzhong Tian, Yong liu
To tackle this problem, we propose a novel domain-adaptive degradation network for face super-resolution in the wild.
1 code implementation • NeurIPS 2021 • Chenxin Tao, Zizhang Li, Xizhou Zhu, Gao Huang, Yong liu, Jifeng Dai
In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.
no code implementations • 3 Dec 2021 • Jie Zhu, Huabin Huang, Banghuai Li, Yong liu, Leye Wang
Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.
no code implementations • NeurIPS 2021 • Yong liu
In this paper, we study the statistical properties of kernel $k$-means and Nystr\"{o}m-based kernel $k$-means, and obtain optimal clustering risk bounds, which improve the existing risk bounds.
no code implementations • NeurIPS 2021 • Shaojie Li, Yong liu
In the smoothness scenario, we provide generalization bounds that are not only a logarithmic dependency on the label set cardinality but a faster convergence rate of order $\mathcal{O}(\frac{1}{n})$ on the sample size $n$.
no code implementations • NeurIPS 2021 • Shaogao Lv, Junhui Wang, Jiankun Liu, Yong liu
In this paper, we provide theoretical results of estimation bounds and excess risk upper bounds for support vector machine (SVM) with sparse multi-kernel representation.
no code implementations • 25 Nov 2021 • Wen Yu, Baiying Lei, Yanyan Shen, Shuqiang Wang, Yong liu, Zhiguang Feng, Yong Hu, Michael K. Ng
In this work, a novel Multidirectional Perception Generative Adversarial Network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages.
no code implementations • 21 Nov 2021 • Zizhang Li, Mengmeng Wang, Jianbiao Mei, Yong liu
Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions.
Ranked #1 on Referring Expression Segmentation on G-Ref test B
no code implementations • 17 Nov 2021 • Yulan Hu, Yong liu
Benefiting from the strong ability of the pre-trained model, the research on Chinese Word Segmentation (CWS) has made great progress in recent years.
no code implementations • 16 Nov 2021 • Jun Chen, Tianxin Huang, Wenzhou Chen, Yong liu
During the training process of the neural network, we observe that its metric will also regularly converge to the linearly nearly Euclidean metric, which is consistent with the convergent behavior of linearly nearly Euclidean metrics under the Ricci-DeTurck flow.
no code implementations • 14 Nov 2021 • Shihao Shao, Yong liu, Qinghua Cui
Here we presented a layer-stress deep learning framework (x-NN) which implemented automatic and wise depth decision on shallow or deep feature map in a deep network through firstly designing enough number of layers and then trading off them by Multi-Head Attention Block.
no code implementations • 9 Nov 2021 • Shaojie Li, Yong liu
We first successfully establish learning rates for these algorithms in a general nonconvex setting, where the analysis sheds insights on the trade-off between optimization and generalization and the role of early-stopping.
no code implementations • 4 Nov 2021 • WeiFu Fu, Congchong Nie, Ting Sun, Jun Liu, Tianliang Zhang, Yong liu
Our method focuses on the problem in following two aspects: the long-tail distribution and the segmentation quality of mask and boundary.
Ranked #3 on Instance Segmentation on LVIS v1.0 val
no code implementations • 28 Oct 2021 • Mengmeng Wang, Xiaoqian Yang, Yong liu
Visual object tracking performance has been dramatically improved in recent years, but some severe challenges remain open, like distractors and occlusions.