no code implementations • 7 Jan 2025 • Lingzhi Yuan, Xinfeng Li, Chejian Xu, Guanhong Tao, Xiaojun Jia, Yihao Huang, Wei Dong, Yang Liu, XiaoFeng Wang, Bo Li
Text-to-image (T2I) models have been shown to be vulnerable to misuse, particularly in generating not-safe-for-work (NSFW) content, raising serious ethical concerns.
no code implementations • 30 Dec 2024 • Han Zhou, Wei Dong, Xiaohong Liu, Yulun Zhang, Guangtao Zhai, Jun Chen
Although significant progress has been made in enhancing visibility, retrieving texture details, and mitigating noise in Low-Light (LL) images, the challenge persists in applying current Low-Light Image Enhancement (LLIE) methods to real-world scenarios, primarily due to the diverse illumination conditions encountered.
1 code implementation • 27 Dec 2024 • Haoyang Li, Yiming Li, Anxin Tian, Tianhao Tang, Zhanchao Xu, Xuejia Chen, Nicole Hu, Wei Dong, Qing Li, Lei Chen
This survey provides a comprehensive overview of KV cache management strategies for LLM acceleration, categorizing them into token-level, model-level, and system-level optimizations.
no code implementations • 1 Nov 2024 • Ziting Wang, Haitao Yuan, Wei Dong, Gao Cong, Feifei Li
We employ a Monte Carlo Tree Search (MCTS) based policy framework to find optimal chunk combinations sequentially, allowing for a comprehensive consideration of correlations among chunks.
no code implementations • 30 Oct 2024 • Wei Dong, Yuan Sun, Yiting Yang, Xing Zhang, Zhijun Lin, Qingsen Yan, Haokui Zhang, Peng Wang, Yang Yang, HengTao Shen
A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix.
1 code implementation • 28 Oct 2024 • Wei Dong, Han Zhou, Yulun Zhang, Xiaohong Liu, Jun Chen
Inspired by Mamba which demonstrates powerful and highly efficient sequence modeling, we introduce a novel framework based on Mamba for Exposure Correction (ECMamba) with dual pathways, each dedicated to the restoration of reflectance and illumination map, respectively.
no code implementations • 25 Oct 2024 • Huajian Liu, Wei Dong, Kunpeng Fan, Chao Wang, Yongzhuo Gao
Analyzing and forecasting trajectories of agents like pedestrians plays a pivotal role for embodied intelligent applications.
no code implementations • 15 Sep 2024 • Dawei Yan, Pengcheng Li, Yang Li, Hao Chen, QingGuo Chen, Weihua Luo, Wei Dong, Qingsen Yan, Haokui Zhang, Chunhua Shen
In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction.
no code implementations • 28 Jul 2024 • Zeyu Chen, Pengfei Zhang, Kai Ye, Wei Dong, Xin Feng, Yana Zhang
In reality, a video can use different music as background music, and a music can be used as background music for different videos.
1 code implementation • 17 Jul 2024 • Han Zhou, Wei Dong, Xiaohong Liu, Shuaicheng Liu, Xiongkuo Min, Guangtao Zhai, Jun Chen
Most existing Low-light Image Enhancement (LLIE) methods either directly map Low-Light (LL) to Normal-Light (NL) images or use semantic or illumination maps as guides.
Ranked #1 on
Low-Light Image Enhancement
on LOLv2
1 code implementation • CVPRW 2024 • Wei Dong, Han Zhou, Ruiyi Wang, Xiaohong Liu, Guangtao Zhai, Jun Chen
Image dehazing, a pivotal task in low-level vision, aims to restore the visibility and detail from hazy images.
Ranked #1 on
Nonhomogeneous Image Dehazing
on DNH-HAZE
1 code implementation • 22 Apr 2024 • Kangzhen Yang, Tao Hu, Kexin Dai, Genggeng Chen, Yu Cao, Wei Dong, Peng Wu, Yanning Zhang, Qingsen Yan
In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images.
3 code implementations • 22 Apr 2024 • Xiaoning Liu, Zongwei Wu, Ao Li, Florin-Alexandru Vasluianu, Yulun Zhang, Shuhang Gu, Le Zhang, Ce Zhu, Radu Timofte, Zhi Jin, Hongjun Wu, Chenxi Wang, Haitao Ling, Yuanhao Cai, Hao Bian, Yuxin Zheng, Jing Lin, Alan Yuille, Ben Shao, Jin Guo, Tianli Liu, Mohao Wu, Yixu Feng, Shuo Hou, Haotian Lin, Yu Zhu, Peng Wu, Wei Dong, Jinqiu Sun, Yanning Zhang, Qingsen Yan, Wenbin Zou, Weipeng Yang, Yunxiang Li, Qiaomu Wei, Tian Ye, Sixiang Chen, Zhao Zhang, Suiyi Zhao, Bo wang, Yan Luo, Zhichao Zuo, Mingshen Wang, Junhu Wang, Yanyan Wei, Xiaopeng Sun, Yu Gao, Jiancheng Huang, Hongming Chen, Xiang Chen, Hui Tang, Yuanbin Chen, Yuanbo Zhou, Xinwei Dai, Xintao Qiu, Wei Deng, Qinquan Gao, Tong Tong, Mingjia Li, Jin Hu, Xinyu He, Xiaojie Guo, sabarinathan, K Uma, A Sasithradevi, B Sathya Bama, S. Mohamed Mansoor Roomi, V. Srivatsav, Jinjuan Wang, Long Sun, Qiuying Chen, Jiahong Shao, Yizhi Zhang, Marcos V. Conde, Daniel Feijoo, Juan C. Benito, Alvaro García, Jaeho Lee, Seongwan Kim, Sharif S M A, Nodirkhuja Khujaev, Roman Tsoy, Ali Murtaza, Uswah Khairuddin, Ahmad 'Athif Mohd Faudzi, Sampada Malagi, Amogh Joshi, Nikhil Akalwadi, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudenagudi, Wenyi Lian, Wenjing Lian, Jagadeesh Kalyanshetti, Vijayalaxmi Ashok Aralikatti, Palani Yashaswini, Nitish Upasi, Dikshit Hegde, Ujwala Patil, Sujata C, Xingzhuo Yan, Wei Hao, Minghan Fu, Pooja Choksy, Anjali Sarvaiya, Kishor Upla, Kiran Raja, Hailong Yan, Yunkai Zhang, Baiang Li, Jingyi Zhang, Huan Zheng
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results.
1 code implementation • 21 Apr 2024 • Genggeng Chen, Kexin Dai, Kangzhen Yang, Tao Hu, Xiangyu Chen, Yongqing Yang, Wei Dong, Peng Wu, Yanning Zhang, Qingsen Yan
Specifically, we employ two modules for feature extraction: shared weight modules and non-shared weight modules.
1 code implementation • 18 Apr 2024 • Wei Dong, Han Zhou, Yuqiong Tian, Jingke Sun, Xiaohong Liu, Guangtao Zhai, Jun Chen
Shadow-affected images often exhibit pronounced spatial discrepancies in color and illumination, consequently degrading various vision applications including object detection and segmentation systems.
Ranked #1 on
Shadow Removal
on WSRD+
1 code implementation • CVPR 2024 • Wei Dong, Xing Zhang, Bihui Chen, Dawei Yan, Zhijun Lin, Qingsen Yan, Peng Wang, Yang Yang
Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.
1 code implementation • 8 Feb 2024 • Qingsen Yan, Yixu Feng, Cheng Zhang, Pei Wang, Peng Wu, Wei Dong, Jinqiu Sun, Yanning Zhang
Further, we design a novel Color and Intensity Decoupling Network (CIDNet) with two branches dedicated to processing the decoupled image brightness and color in the HVI space.
Ranked #1 on
Low-Light Image Enhancement
on LOL-v2
Low-light Image Deblurring and Enhancement
Low-Light Image Enhancement
1 code implementation • 23 Jan 2024 • Lincan Li, Wei Shao, Wei Dong, Yijun Tian, Qiming Zhang, Kaixiang Yang, Wenjie Zhang
There has been a huge bottleneck regarding the upper bound of autonomous driving algorithm performance, a consensus from academia and industry believes that the key to surmount the bottleneck lies in data-centric autonomous driving technology.
no code implementations • 2 Nov 2023 • Qingsen Yan, Tao Hu, Yuan Sun, Hao Tang, Yu Zhu, Wei Dong, Luc van Gool, Yanning Zhang
To address this challenge, we formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition, consisting of the feature condition generator and the noise predictor.
1 code implementation • NeurIPS 2023 • Wei Dong, Dawei Yan, Zhijun Lin, Peng Wang
Consequently, effectively adapting large pre-trained models to downstream tasks in an efficient manner has become a prominent research area.
no code implementations • CVPR 2023 • Wei Dong, Chris Choy, Charles Loop, Or Litany, Yuke Zhu, Anima Anandkumar
To apply this representation to monocular scene reconstruction, we develop a scale calibration algorithm for fast geometric initialization from monocular depth priors.
1 code implementation • 8 May 2023 • Han Zhou, Wei Dong, Yangyi Liu, Jun Chen
To tackle these two challenges, we propose a novel two branch network that leverages 2D discrete wavelete transform (DWT), fast Fourier convolution (FFC) residual block and a pretrained ConvNeXt model.
1 code implementation • 28 Mar 2023 • Deze Wang, Boxing Chen, Shanshan Li, Wei Luo, Shaoliang Peng, Wei Dong, Xiangke Liao
To alleviate the potentially catastrophic forgetting issue in multilingual models, we fix all pre-trained model parameters, insert the parameter-efficient structure adapter, and fine-tune it.
1 code implementation • 9 Feb 2023 • Wei Dong, Dawei Yan, Peng Wang
Considering the excessive memory overheads of contrastive learning, we further propose a negative-free solution, where the main contribution is a Graph Signal Decorrelation (GSD) constraint to avoid representation collapse and over-smoothing.
no code implementations • 17 Sep 2022 • Shuyang Shi, Yuzhu Li, Wei Dong
Then, adaptive estimation laws for mass-inertia parameters are designed based on a filter operation.
2 code implementations • 28 May 2022 • Wei Dong, Yuting Liang, Ke Yi
In this paper, we present two new algorithms for covariance estimation under concentrated differential privacy (zCDP).
2 code implementations • CVPR 2022 • Wei Dong, Junsheng Wu, Yi Luo, ZongYuan Ge, Peng Wang
In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing.
no code implementations • 6 Dec 2021 • Wei Dong, Kwonyoung Ryu, Michael Kaess, Jaesik Park
We further collect a dataset of indoor and outdoor LiDAR scenes in the posed range image format.
1 code implementation • 4 Dec 2021 • Deze Wang, Zhouyang Jia, Shanshan Li, Yue Yu, Yun Xiong, Wei Dong, Xiangke Liao
In this paper, we propose an approach to bridge pre-trained models and code-related tasks.
no code implementations • 1 Oct 2021 • Wei Dong, Yixing Lao, Michael Kaess, Vladlen Koltun
Unlike existing GPU hash maps, the ASH framework provides a versatile tensor interface, hiding low-level details from the users.
1 code implementation • 24 Mar 2021 • Chen Zeng, Yue Yu, Shanshan Li, Xin Xia, Zhiming Wang, Mingyang Geng, Bailin Xiao, Wei Dong, Xiangke Liao
With the rapid increase in the amount of public code repositories, developers maintain a great desire to retrieve precise code snippets by using natural language.
2 code implementations • CVPR 2021 • Heng Yang, Wei Dong, Luca Carlone, Vladlen Koltun
We present self-supervised geometric perception (SGP), the first general framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels (e. g., camera poses, rigid transformations).
no code implementations • 5 Nov 2020 • Akash Sharma, Wei Dong, Michael Kaess
We present a fast, scalable, and accurate Simultaneous Localization and Mapping (SLAM) system that represents indoor scenes as a graph of objects.
no code implementations • 16 Oct 2020 • Zhoujian Sun, Wei Dong, Jinlong Shi, Zhengxing Huang
In the disease prediction task, our model achieves 0. 743 and 0. 639 in terms of macro area under the curve (AUC) in predicting 53 circulation system diseases in the two datasets, respectively.
2 code implementations • CVPR 2020 • Christopher Choy, Wei Dong, Vladlen Koltun
We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans.
Ranked #2 on
Point Cloud Registration
on KITTI (FCGF setting)
1 code implementation • Journal of Biomedical Informatics 2019 • Peipei Chen, Wei Dong, Xudong, Uzay Kaymak, Kunlun He, Zhengxing Huang
We propose a novel hybrid model bridging multi-task deep learning and K-nearest neighbors (KNN) for ITE estimation.
Ranked #3 on
Causal Inference
on IHDP
no code implementations • 13 Oct 2019 • Gang Chen, Hongzhe Yu, Wei Dong, Xinjun Sheng, Xiangyang Zhu, Han Ding
While training an end-to-end navigation network in the real world is usually of high cost, simulation provides a safe and cheap environment in this training stage.
no code implementations • IJCNLP 2019 • Wei Dong, Qinliang Su, Dinghan Shen, Changyou Chen
Hashing is promising for large-scale information retrieval tasks thanks to the efficiency of distance evaluation between binary codes.
no code implementations • 1 Jun 2019 • Jason L. Causey, Yuanfang Guan, Wei Dong, Karl Walker, Jake A. Qualls, Fred Prior, Xiuzhen Huang
We applied to this cohort our newly developed algorithm, DeepScreener, which is based on a novel deep learning approach.
no code implementations • 25 Nov 2018 • Fei Xue, Qiuyuan Wang, Xin Wang, Wei Dong, Junqiu Wang, Hongbin Zha
We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks.
no code implementations • 17 Nov 2018 • Chengdong Feng, Zhenbang Chen, Weijiang Hong, Hengbiao Yu, Wei Dong, Ji Wang
How to ensure the safety of DNN-based system is a critical problem for the research and application of DNN.
no code implementations • ECCV 2018 • Wei Dong, Qiuyuan Wang, Xin Wang, Hongbin Zha
We propose a novel 3D spatial representation for data fusion and scene reconstruction.