no code implementations • Findings (EMNLP) 2021 • Xin Lu, Yijian Tian, Yanyan Zhao, Bing Qin
To address this problem, we propose a simple and effective Retrieve-Discriminate-Rewrite framework.
no code implementations • 19 Apr 2025 • Zichuan Liu, Liming Jiang, Qing Yan, Yumin Jia, Hao Kang, Xin Lu
Given a reference face and a text prompt, FaceCLIP produces a unified representation that encodes both identity and text, which conditions a base diffusion model to generate images that are identity-consistent and text-aligned.
1 code implementation • 16 Apr 2025 • Lei Sun, Andrea Alfarano, Peiqi Duan, Shaolin Su, Kaiwei Wang, Boxin Shi, Radu Timofte, Danda Pani Paudel, Luc van Gool, Qinglin Liu, Wei Yu, Xiaoqian Lv, Lu Yang, Shuigen Wang, Shengping Zhang, Xiangyang Ji, Long Bao, Yuqiang Yang, Jinao Song, Ziyi Wang, Shuang Wen, Heng Sun, Kean Liu, Mingchen Zhong, Senyan Xu, Zhijing Sun, Jiaying Zhu, Chengjie Ge, Xingbo Wang, Yidi Liu, Xin Lu, Xueyang Fu, Zheng-Jun Zha, Dawei Fan, Dafeng Zhang, Yong Yang, Siru Zhang, Qinghua Yang, Hao Kang, Huiyuan Fu, Heng Zhang, Hongyuan Yu, Zhijuan Huang, Shuoyan Wei, Feng Li, Runmin Cong, Weiqi Luo, Mingyun Lin, Chenxu Jiang, Hongyi Liu, Lei Yu, WeiLun Li, Jiajun Zhai, Tingting Lin, Shuang Ma, Sai Zhou, Zhanwen Liu, Yang Wang, Eiffel Chong, Nuwan Bandara, Thivya Kandappu, Archan Misra, Yihang Chen, Zhan Li, Weijun Yuan, Wenzhuo Wang, Boyang Yao, Zhanglu Chen, Yijing Sun, Tianjiao Wan, Zijian Gao, Qisheng Xu, Kele Xu, Yukun Zhang, Yu He, Xiaoyan Xie, Tao Fu, Yashu Gautamkumar Patel, Vihar Ramesh Jain, Divesh Basina, Rishik Ashili, Manish Kumar Manjhi, Sourav Kumar, Prinon Benny, Himanshu Ghunawat, B Sri Sairam Gautam, Anett Varghese, Abhishek Yadav
This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results.
no code implementations • 12 Apr 2025 • Hao Kang, Stathi Fotiadis, Liming Jiang, Qing Yan, Yumin Jia, Zichuan Liu, Min Jin Chong, Xin Lu
We propose a simple yet effective zero-shot framework for subject-driven image generation using a vanilla Flux model.
1 code implementation • 20 Mar 2025 • Liming Jiang, Qing Yan, Yumin Jia, Zichuan Liu, Hao Kang, Xin Lu
Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX.
no code implementations • 14 Jan 2025 • Xin Lu
Accurate prediction of electricity prices plays an essential role in the electricity market.
no code implementations • 9 Jan 2025 • Xin Lu, Jing Qiu, Cuo Zhang, Gang Lei, Jianguo Zhu
To incentivize these high price-tolerance residential prosumers to participate in SES, a novel SES aggregation framework is proposed, which does not require prosumers to take additional actions and allows them to maintain existing energy storage patterns.
no code implementations • 15 Dec 2024 • Di wu, Xin Lu, Yanyan Zhao, Bing Qin
A key issue is that fine-tuning often compromises the safety alignment of LLMs.
no code implementations • 13 Dec 2024 • Yu-Jhe Li, Xinyang Zhang, Kun Wan, Lantao Yu, Ajinkya Kale, Xin Lu
To overcome this challenge, existing methods often use multi-modal models like CLIP, which combine image and text features in a shared embedding space to bridge the gap between limited and extensive vocabulary recognition, resulting in a two-stage approach: In the first stage, a mask generator takes an input image to generate mask proposals, and the in the second stage the target mask is picked based on the query.
no code implementations • 9 Nov 2024 • Shukun Jia, Yichao Cao, Feng Yang, Xin Lu, Xiaobo Lu
Multi-object tracking is advancing through two dominant paradigms: traditional tracking by detection and newly emerging tracking by query.
no code implementations • 29 Sep 2024 • Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu, Yongbo Wang, Feng Wang, Jingtong Wu, Xin Lu, Rui Yan
During inference, the optimized coefficients are fixed to re-weight these heads, regardless of the specific task at hand.
no code implementations • 31 Aug 2024 • XiaoYu Zhang, Wenchuan Yang, Jiawei Feng, Bitao Dai, Tianci Bu, Xin Lu
Compared with other methods, we use graph wavelet neural networks for the convolution layer of the model, which aggregates multi-scale messages to generate graph representations.
no code implementations • 16 Aug 2024 • Rongxuan Wang, Xin Lu, Xiaoyang Liu, Xiaoyi Zou, Tongyi Cao, Ying Li
To address this issue, we introduce PriorMapNet to enhance online vectorized HD map construction with priors.
no code implementations • 1 Aug 2024 • Mingcong Lu, Jiangcai Zhu, Wang Hao, Zheng Li, Shusheng Zhang, Kailai Shao, Chao Chen, Nan Li, Feng Wang, Xin Lu
In this way, ISM is able to maintain the high quality of prefix LLM and low generation latency of causal LLM, simultaneously.
no code implementations • 11 Jul 2024 • Chang Sun, Hui Yuan, Shuai Li, Xin Lu, Raouf Hamzaoui
In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss function.
no code implementations • 11 Jul 2024 • Chang Sun, Hui Yuan, Xiaolong Mao, Xin Lu, Raouf Hamzaoui
The proposed module can predict the number of occupied child nodes and map it into an 8- dimensional vector to assist the context model in predicting the probability distribution of the occupancy of the current node for efficient entropy coding.
no code implementations • 8 Jul 2024 • Xiaolong Mao, Hui Yuan, Xin Lu, Raouf Hamzaoui, Wei Gao
Learning-based methods have proven successful in compressing geometric information for point clouds.
1 code implementation • 2 Jul 2024 • Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen
The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse.
no code implementations • 21 Jun 2024 • Mingyuan Wu, Zichuan Liu, Haozhen Zheng, Hongpeng Guo, Bo Chen, Xin Lu, Klara Nahrstedt
To address this, we propose and formulate a one tap driven single instance segmentation task that segments a single instance selected by a user via a positive tap.
no code implementations • 11 Jun 2024 • Wenchuan Yang, Cheng Yang, Jichao Li, Yuejin Tan, Xin Lu, Chuan Shi
The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation.
no code implementations • 26 Apr 2024 • XiaoYu Zhang, Pengcheng Yang, Jiawei Feng, Qiang Luo, Wei Lin, Xin Lu
The results revealed that even with rudimentary neuronal activation mechanisms, models grounded in real neural network structures can generate activation patterns strikingly similar to those observed in the actual brain.
no code implementations • 13 Mar 2024 • Hongyang Zhu, Xin Lu, Yanwei Qin, Xinran Yu, Tianjiao Sun, Yunsong Zhao
The proposed model corrects the vertical stripe artifacts on the sinogram by innovatively updating the response inconsistency compensation coefficients of detector units, which is achieved by employing the group sparse constraint and the projection-view direction sparse constraint on the stripe artifacts.
no code implementations • 4 Mar 2024 • Xin Lu, Yanyan Zhao, Bing Qin, Liangyu Huo, Qing Yang, Dongliang Xu
Through analysis, we found the contribution ratio of Multi-Head Attention (a combination function) to pre-trained language modeling is a key factor affecting base capabilities.
no code implementations • 4 Mar 2024 • Xin Lu, Yanyan Zhao, Bing Qin
However, studies have indicated that MoE Transformers underperform vanilla Transformers in many downstream tasks, significantly diminishing the practical value of MoE models.
no code implementations • CVPR 2024 • Yichen Sheng, Zixun Yu, Lu Ling, Zhiwen Cao, Xuaner Zhang, Xin Lu, Ke Xian, Haiting Lin, Bedrich Benes
Dr. Bokeh then takes the layered representation and user-defined lens parameters to render photo-realistic lens blur based on the novel occlusion-aware bokeh rendering method.
no code implementations • 10 Nov 2023 • Xin Lu, Shikun Chen, Yichao Cao, Xin Zhou, Xiaobo Lu
To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval.
no code implementations • 7 Oct 2023 • Zhixuan Chu, Huaiyu Guo, Xinyuan Zhou, Yijia Wang, Fei Yu, Hong Chen, Wanqing Xu, Xin Lu, Qing Cui, Longfei Li, Jun Zhou, Sheng Li
Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance.
no code implementations • 7 Sep 2023 • Chengmin Zhou, Xin Lu, Jiapeng Dai, Bingding Huang, Xiaoxu Liu, Pasi Fränti
Reinforcement learning algorithms generate optimal or near-optimal time-sequential predictions.
no code implementations • 19 Jul 2023 • Xinyang Zhang, Wentian Zhao, Xin Lu, Jeff Chien
To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation.
no code implementations • 19 Apr 2023 • Weixiang Zhao, Yanyan Zhao, Xin Lu, Shilong Wang, Yanpeng Tong, Bing Qin
This report presents a study on the emotional dialogue capability of ChatGPT, an advanced language model developed by OpenAI.
no code implementations • 21 Dec 2022 • Lewis Marsh, Felix Y. Zhou, Xiao Qin, Xin Lu, Helen M. Byrne, Heather A. Harrington
Organoids are multi-cellular structures which are cultured in vitro from stem cells to resemble specific organs (e. g., brain, liver) in their three-dimensional composition.
no code implementations • 4 Nov 2022 • Jiehua Zhang, Xueyang Zhang, Zhuo Su, Zitong Yu, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu
For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56. 1% on the ImageNet dataset, which is nearly 9% higher than the baseline.
1 code implementation • 11 Oct 2022 • Jingru Tan, Bo Li, Xin Lu, Yongqiang Yao, Fengwei Yu, Tong He, Wanli Ouyang
Long-tail distribution is widely spread in real-world applications.
1 code implementation • 11 Oct 2022 • Bo Li, Yongqiang Yao, Jingru Tan, Xin Lu, Fengwei Yu, Ye Luo, Jianwei Lu
Specifically, there are an object detection task (consisting of an instance-classification task and a localization task) and an image-classification task in our framework, responsible for utilizing the two types of supervision.
1 code implementation • 8 Oct 2022 • Weixiang Zhao, Yanyan Zhao, Xin Lu, Bing Qin
As a critical step to achieve human-like chatbots, empathetic response generation has attained increasing interests.
no code implementations • 7 Oct 2022 • Lei Cui, Yangguang Li, Xin Lu, Dong An, Fenggang Liu
Bayesian Optimization (BO) is a common solution to search optimal hyperparameters based on sample observations of a machine learning model.
1 code implementation • 15 Jun 2022 • Renee S. Hoekzema, Lewis Marsh, Otto Sumray, Thomas M. Carroll, Xin Lu, Helen M. Byrne, Heather A. Harrington
Analysis of single-cell transcriptomics often relies on clustering cells and then performing differential gene expression (DGE) to identify genes that vary between these clusters.
1 code implementation • 8 Jun 2022 • Zhiyuan You, Lei Cui, Yujun Shen, Kai Yang, Xin Lu, Yu Zheng, Xinyi Le
For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88. 1% to 96. 5%) and anomaly localization (from 89. 5% to 96. 8%).
Ranked #3 on
Multi-class Anomaly Detection
on MVTec AD
1 code implementation • 22 Jan 2022 • Zhiyuan You, Kai Yang, Wenhan Luo, Xin Lu, Lei Cui, Xinyi Le
This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i. e., described by one or several support images) occurring in the query image.
Ranked #2 on
Object Counting
on CARPK
1 code implementation • 19 Dec 2021 • Wenbo Li, Xin Lu, Shengju Qian, Jiangbo Lu, Xiangyu Zhang, Jiaya Jia
Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems.
Ranked #11 on
Image Super-Resolution
on Set5 - 2x upscaling
(using extra training data)
2 code implementations • 8 Dec 2021 • Xiaojie Chu, Liangyu Chen, Chengpeng Chen, Xin Lu
Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images.
Ranked #1 on
Color Image Denoising
on Urban100 sigma30
no code implementations • 8 Oct 2021 • Jiehua Zhang, Zhuo Su, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu
The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs.
1 code implementation • 17 May 2021 • Andrey Ignatov, Kim Byeoung-su, Radu Timofte, Angeline Pouget, Fenglong Song, Cheng Li, Shuai Xiao, Zhongqian Fu, Matteo Maggioni, Yibin Huang, Shen Cheng, Xin Lu, Yifeng Zhou, Liangyu Chen, Donghao Liu, Xiangyu Zhang, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Minsu Kwon, Myungje Lee, Jaeyoon Yoo, Changbeom Kang, Shinjo Wang, Bin Huang, Tianbao Zhou, Shuai Liu, Lei Lei, Chaoyu Feng, Liguang Huang, Zhikun Lei, Feifei Chen
A detailed description of all models developed in the challenge is provided in this paper.
2 code implementations • 13 May 2021 • Liangyu Chen, Xin Lu, Jie Zhang, Xiaojie Chu, Chengpeng Chen
Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.
Ranked #3 on
Single Image Deraining
on Test2800
1 code implementation • CVPR 2021 • Gang Zhang, Xin Lu, Jingru Tan, Jianmin Li, Zhaoxiang Zhang, Quanquan Li, Xiaolin Hu
In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner.
1 code implementation • IWCS (ACL) 2021 • Gene Louis Kim, Viet Duong, Xin Lu, Lenhart Schubert
"Episodic Logic:Unscoped Logical Form" (EL-ULF) is a semantic representation capturing predicate-argument structure as well as more challenging aspects of language within the Episodic Logic formalism.
no code implementations • 22 Feb 2021 • Feng Du, Shuaishuai Luo, Brenden R. Ortiz, Ye Chen, Weiyin Duan, Dongting Zhang, Xin Lu, Stephen D. Wilson, Yu Song, Huiqiu Yuan
Beyond $p\approx10$ GPa, a second superconducting dome emerges with maximum $T_{\rm c}\approx1. 0$ K at $p_{\rm c2}\approx22$ GPa, which becomes fully suppressed at $p\approx28$ GPa.
Superconductivity
no code implementations • 21 Jan 2021 • Yuan Fang, Ding Wang, Peng Li, Hang Su, Tian Le, Yi Wu, Guo-Wei Yang, Hua-Li Zhang, Zhi-Guang Xiao, Yan-Qiu Sun, Si-Yuan Hong, Yan-Wu Xie, Huan-Hua Wang, Chao Cao, Xin Lu, Hui-Qiu Yuan, Yang Liu
We report growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films on Si(111).
Mesoscale and Nanoscale Physics
2 code implementations • CVPR 2021 • Jingru Tan, Xin Lu, Gang Zhang, Changqing Yin, Quanquan Li
To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally.
Ranked #18 on
Instance Segmentation
on LVIS v1.0 val
no code implementations • COLING 2020 • Xin Lu, Yanyan Zhao, Yang Wu, Yijian Tian, Huipeng Chen, Bing Qin
We noticed that the gold emotion labels of the context utterances can provide explicit and accurate emotion interaction, but it is impossible to input gold labels at inference time.
Ranked #46 on
Emotion Recognition in Conversation
on IEMOCAP
no code implementations • ECCV 2020 • Xin Lu, Quanquan Li, Buyu Li, Junjie Yan
In this paper, we propose MimicDet, a novel and efficient framework to train a one-stage detector by directly mimic the two-stage features, aiming to bridge the accuracy gap between one-stage and two-stage detectors.
no code implementations • 28 Jul 2020 • Xin Lu, Mark-Oliver Goerbig
We investigate possible hybridization between these interface states as a function of the width of the topological material and of the characteristic interface size.
Mesoscale and Nanoscale Physics High Energy Physics - Theory Quantum Physics
no code implementations • 7 Jun 2020 • Xin Lu
In machine learning, observation features are measured in a metric space to obtain their distance function for optimization.
142 code implementations • 17 Jun 2019 • Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin
In this paper, we introduce the various features of this toolbox.
2 code implementations • 13 Jun 2019 • Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan
Grid R-CNN is a well-performed objection detection framework.
no code implementations • 15 Apr 2019 • Sharib Ali, Felix Zhou, Adam Bailey, Barbara Braden, James East, Xin Lu, Jens Rittscher
Given the widespread use of endoscopy in different clinical applications, we contend that the robust and reliable identification of such artifacts and the automated restoration of corrupted video frames is a fundamental medical imaging problem.
no code implementations • CVPR 2019 • Wei Xiong, Jiahui Yu, Zhe Lin, Jimei Yang, Xin Lu, Connelly Barnes, Jiebo Luo
We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting.
2 code implementations • CVPR 2019 • Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan
This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.
Ranked #10 on
2D Object Detection
on SARDet-100K
no code implementations • ECCV 2018 • Rameswar Panda, Jianming Zhang, Haoxiang Li, Joon-Young Lee, Xin Lu, Amit K. Roy-Chowdhury
While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts.
1 code implementation • ECCV 2018 • Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang
Existing video prediction methods mainly rely on observing multiple historical frames or focus on predicting the next one-frame.
30 code implementations • ICCV 2019 • Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas Huang
We present a generative image inpainting system to complete images with free-form mask and guidance.
Ranked #3 on
Image Inpainting
on Places2 val
3 code implementations • ICLR 2018 • Jianbo Ye, Xin Lu, Zhe Lin, James Z. Wang
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios.
28 code implementations • CVPR 2018 • Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas S. Huang
Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.
1 code implementation • CVPR 2018 • Licheng Yu, Zhe Lin, Xiaohui Shen, Jimei Yang, Xin Lu, Mohit Bansal, Tamara L. Berg
In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression.
Generalized Referring Expression Segmentation
Referring Expression
+1
1 code implementation • ICCV 2017 • Wei-Chih Hung, Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang
We present a scene parsing method that utilizes global context information based on both the parametric and non- parametric models.
15 code implementations • NeurIPS 2017 • Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang
The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer.
1 code implementation • ICCV 2017 • Chenxi Liu, Zhe Lin, Xiaohui Shen, Jimei Yang, Xin Lu, Alan Yuille
In this paper we are interested in the problem of image segmentation given natural language descriptions, i. e. referring expressions.
no code implementations • CVPR 2017 • Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang
Recent progresses on deep discriminative and generative modeling have shown promising results on texture synthesis.
2 code implementations • CVPR 2017 • Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang
Compositing is one of the most common operations in photo editing.
1 code implementation • CVPR 2017 • Chao Yang, Xin Lu, Zhe Lin, Eli Shechtman, Oliver Wang, Hao Li
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal.
no code implementations • ICCV 2015 • Xin Lu, Zhe Lin, Xiaohui Shen, Radomir Mech, James Z. Wang
We propose a deep multi-patch aggregation network training approach, which allows us to train models using multiple patches generated from one image.
Ranked #8 on
Aesthetics Quality Assessment
on AVA