68 citations · 125 across the 13 of their papers we have counts for
13 papers
Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation
Yinsong Xu, Aidong Men, Yang Liu +2
In deep learning, initializing models with pre-trained weights has become the de facto practice for various downstream tasks. Many unsupervised domain adaptation (UDA) methods typi…
Causality-based Dual-Contrastive Learning Framework for Domain Generalization
Zining Chen, Weiqiu Wang, Zhicheng Zhao +1
Domain Generalization (DG) is essentially a sub-branch of out-of-distribution generalization, which trains models from multiple source domains and generalizes to unseen target doma…
Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation
Jiangbo Pei, Zhuqing Jiang, Aidong Men +3
Source-free unsupervised domain adaptation (SFUDA) aims to learn a target domain model using unlabeled target data and the knowledge of a well-trained source domain model. Most pre…
Delving into the Continuous Domain Adaptation
Yinsong Xu, Zhuqing Jiang, Aidong Men +2
Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e.g., art, real, painting, quickdraw, etc. We argue that…
Bag of Tricks for Out-of-Distribution Generalization
Zining Chen, Weiqiu Wang, Zhicheng Zhao +2
Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strateg…
Seeing your sleep stage: cross-modal distillation from EEG to infrared video
Jianan Han, Shaoxing Zhang, Aidong Men +4
It is inevitably crucial to classify sleep stage for the diagnosis of various diseases. However, existing automated diagnosis methods mostly adopt the "gold-standard" lectroencepha…
Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing
Jianning Wu, Zhuqing Jiang, Shiping Wen +2
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 embed…
Taylor saves for later: disentanglement for video prediction using Taylor representation
Ting Pan, Zhuqing Jiang, Jianan Han +3
Video prediction is a challenging task with wide application prospects in meteorology and robot systems. Existing works fail to trade off short-term and long-term prediction perfor…
Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
Zhuqing Jiang, Chang Liu, Ya'nan Wang +4
With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography. Images capt…
Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
Ya'nan Wang, Zhuqing Jiang, Chang Liu +3
It is suggested that low-light image enhancement realizes one-to-many mapping since we have different definitions of NORMAL-light given application scenarios or users' aesthetic. H…
A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement
Zhuqing Jiang, Haotian Li, Liangjie Liu +2
Self-regularized low-light image enhancement does not require any normal-light image in training, thereby freeing from the chains on paired or unpaired low-/normal-images. However,…
Pyramid Real Image Denoising Network
Yiyun Zhao, Zhuqing Jiang, Aidong Men +1
While deep Convolutional Neural Networks (CNNs) have shown extraordinary capability of modelling specific noise and denoising, they still perform poorly on real-world noisy images.…
Microwave breast cancer detection using Empirical Mode Decomposition features
Hongchao Song, Yunpeng Li, Mark Coates +1
Microwave-based breast cancer detection has been proposed as a complementary approach to compensate for some drawbacks of existing breast cancer detection techniques. Among the exi…