no code implementations • 13 Apr 2024 • Zining Chen, Weiqiu Wang, Zhicheng Zhao, Fei Su, Aidong Men, Hongying Meng
Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target domains share identical categories.
no code implementations • 3 Mar 2024 • Jiangbo Pei, Ruizhe Li, Aidong Men, Yang Liu, Xiahai Zhuang, Qingchao Chen
This paper introduces Zoo-MSFDA, a more general setting that allows each source domain to offer a zoo of multiple source models with different architectures.
no code implementations • IEEE Transactions on Circuits and Systems for Video Technology 2024 • Zining Chen, Weiqiu Wang, Zhicheng Zhao, Fei Su, Member, IEEE, Aidong Men, and Yuan Dong
In this paper, we propose an instance paradigm contrastive learning framework, introducing contrast between original features and novel paradigms to alleviate domain-specific distractions.
no code implementations • 10 Nov 2023 • Yinsong Xu, Jiaqi Tang, Aidong Men, Qingchao Chen
Then, we incorporate the human prior into the prompts, which is vital for alleviating the domain gap between natural and medical images and enhancing the applicability and usefulness of SAM in medical scenarios.
no code implementations • 6 Aug 2023 • Yinsong Xu, Aidong Men, Yang Liu, Qingchao Chen
To answer the first question, we empirically observed an interesting Spontaneous Pulling (SP) Effect in fine-tuning where the discrepancies between any two of the three domains (ImageNet, Source, Target) decrease but at the cost of the impaired semantic structure of the pre-train domain.
no code implementations • 22 Jan 2023 • Zining Chen, Weiqiu Wang, Zhicheng Zhao, Aidong Men
In this paper, we propose a Dual-Contrastive Learning (DCL) module on feature and prototype contrast.
1 code implementation • 30 Aug 2022 • Jiangbo Pei, Zhuqing Jiang, Aidong Men, Liang Chen, Yang Liu, Qingchao Chen
Secondly, based on the UTR, we propose a novel Calibrated Adaption Framework (CAF) for SFUDA, including i)the source knowledge calibration module that guides the target model to learn the transferable source knowledge and discard the non-transferable one, and ii)the target semantics calibration module that calibrates the unreliable semantics.
1 code implementation • 28 Aug 2022 • Yinsong Xu, Zhuqing Jiang, Aidong Men, Yang Liu, Qingchao Chen
Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e. g., art, real, painting, quickdraw, etc.
no code implementations • 23 Aug 2022 • Zining Chen, Weiqiu Wang, Zhicheng Zhao, Aidong Men, Hong Chen
Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue.
1 code implementation • 11 Aug 2022 • Jianan Han, Shaoxing Zhang, Aidong Men, Yang Liu, Ziming Yao, Yan Yan, Qingchao Chen
$S^3VE$ is a large-scale dataset including synchronized infrared video and EEG signal for sleep stage classification, including 105 subjects and 154, 573 video clips that is more than 1100 hours long.
no code implementations • 30 May 2021 • Jianning Wu, Zhuqing Jiang, Shiping Wen, Aidong Men, Haiying Wang
For multimodal tasks, a good feature extraction network should extract information as much as possible and ensure that the extracted feature embedding and other modal feature embedding have an excellent mutual understanding.
no code implementations • 24 May 2021 • Ting Pan, Zhuqing Jiang, Jianan Han, Shiping Wen, Aidong Men, Haiying Wang
We propose a two-branch seq-to-seq deep model to disentangle the Taylor feature and the residual feature in video frames by a novel recurrent prediction module (TaylorCell) and residual module.
no code implementations • 20 Jan 2021 • Zhuqing Jiang, Chang Liu, Ya'nan Wang, Kai Li, Aidong Men, Haiying Wang, Haiyong Luo
With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography.
no code implementations • 4 Jan 2021 • Ya'nan Wang, Zhuqing Jiang, Chang Liu, Kai Li, Aidong Men, Haiying Wang
This paper proposes a neural network for multi-level low-light image enhancement, which is user-friendly to meet various requirements by selecting different images as brightness reference.
no code implementations • 3 Jan 2021 • Zhuqing Jiang, Haotian Li, Liangjie Liu, Aidong Men, Haiying Wang
The generated reflectance, which is assumed to be irrelevant of illumination by Retinex, is treated as enhanced brightness.
1 code implementation • 22 Jun 2020 • Qiulin Zhang, Zhuqing Jiang, Qishuo Lu, Jia'nan Han, Zhengxin Zeng, Shang-Hua Gao, Aidong Men
Therefore, instead of directly removing uncertain redundant features, we propose a \textbf{sp}lit based \textbf{conv}olutional operation, namely SPConv, to tolerate features with similar patterns but require less computation.
4 code implementations • 1 Aug 2019 • Yiyun Zhao, Zhuqing Jiang, Aidong Men, Guodong Ju
Second, at the multi-scale denoising stage, pyramid pooling is utilized to extract multi-scale features.
Ranked #2 on Color Image Denoising on Darmstadt Noise Dataset
no code implementations • 24 Feb 2017 • Hongchao Song, Yunpeng Li, Mark Coates, Aidong Men
One of the most widely used feature extraction method is principle component analysis (PCA).