79 citations · 341 across the 40 of their papers we have counts for
23 papers · 1 filter
Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation
Jingjun Yi, Qi Bi, Hao Zheng +5
The rapid development of Vision Foundation Model (VFM) brings inherent out-domain generalization for a variety of down-stream tasks. Among them, domain generalized semantic segment…
Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing
Zhe Kong, Wentian Zhang, Tao Wang +4
Face recognition systems have raised concerns due to their vulnerability to different presentation attacks, and system security has become an increasingly critical concern. Althoug…
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
Jinheng Xie, Yuexiang Li, Yawen Huang +4
Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images…
Dynamically Masked Discriminator for Generative Adversarial Networks
Wentian Zhang, Haozhe Liu, Bing Li +5
Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However,…
VisorGPT: Learning Visual Prior via Generative Pre-Training
Jinheng Xie, Kai Ye, Yudong Li +5
Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object locat…
Open-World Weakly-Supervised Object Localization
Jinheng Xie, Zhaochuan Luo, Yuexiang Li +3
While remarkable success has been achieved in weakly-supervised object localization (WSOL), current frameworks are not capable of locating objects of novel categories in open-world…
Improving GAN Training via Feature Space Shrinkage
Haozhe Liu, Wentian Zhang, Bing Li +6
Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs…
Interactive Segmentation as Gaussian Process Classification
Minghao Zhou, Hong Wang, Qian Zhao +4
Click-based interactive segmentation (IS) aims to extract the target objects under user interaction. For this task, most of the current deep learning (DL)-based methods mainly foll…
A New Perspective to Boost Vision Transformer for Medical Image Classification
Yuexiang Li, Yawen Huang, Nanjun He +2
Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale lab…
Decoupled Mixup for Generalized Visual Recognition
Haozhe Liu, Wentian Zhang, Jinheng Xie +7
Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models oft…
A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays
Haoqin Ji, Haozhe Liu, Yuexiang Li +7
Accurate abnormality localization in chest X-rays (CXR) can benefit the clinical diagnosis of various thoracic diseases. However, the lesion-level annotation can only be performed…
Combating Mode Collapse in GANs via Manifold Entropy Estimation
Haozhe Liu, Bing Li, Haoqian Wu +5
Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. I…
Robust Representation via Dynamic Feature Aggregation
Haozhe Liu, Haoqin Ji, Yuexiang Li +5
Deep convolutional neural network (CNN) based models are vulnerable to the adversarial attacks. One of the possible reasons is that the embedding space of CNN based model is sparse…
DFTR: Depth-supervised Fusion Transformer for Salient Object Detection
Heqin Zhu, Xu Sun, Yuexiang Li +3
Automated salient object detection (SOD) plays an increasingly crucial role in many computer vision applications. By reformulating the depth information as supervision rather than…
Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix
Ziqi Zhang, Yuexiang Li, Hongxin Wei +3
Deep-learning-based image classification frameworks often suffer from the noisy label problem caused by the inter-observer variation. Recent studies employed learning-to-learn para…
Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint
Jiawei Chen, Yuexiang Li, Kai Ma +1
Convolutional neural network (CNN) have proven its success for semantic segmentation, which is a core task of emerging industrial applications such as autonomous driving. However,…
Aggregative Self-Supervised Feature Learning from a Limited Sample
Jiuwen Zhu, Yuexiang Li, S. Kevin Zhou
Self-supervised learning (SSL) is an efficient approach that addresses the issue of limited training data and annotation shortage. The key part in SSL is its proxy task that define…
Instance-aware Self-supervised Learning for Nuclei Segmentation
Xinpeng Xie, Jiawei Chen, Yuexiang Li +3
Due to the wide existence and large morphological variances of nuclei, accurate nuclei instance segmentation is still one of the most challenging tasks in computational pathology.…
Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning
Jiuwen Zhu, Yuexiang Li, Yifan Hu +1
Deep learning highly relies on the amount of annotated data. However, annotating medical images is extremely laborious and expensive. To this end, self-supervised learning (SSL), a…
Generative Adversarial Networks for Video-to-Video Domain Adaptation
Jiawei Chen, Yuexiang Li, Kai Ma +1
Endoscopic videos from multicentres often have different imaging conditions, e.g., color and illumination, which make the models trained on one domain usually fail to generalize we…
Self-supervised Feature Learning for 3D Medical Images by Playing a Rubik's Cube
Xinrui Zhuang, Yuexiang Li, Yifan Hu +3
Witnessed the development of deep learning, increasing number of studies try to build computer aided diagnosis systems for 3D volumetric medical data. However, as the annotations o…
Active Learning for Breast Cancer Identification
Xinpeng Xie, Yuexiang Li, Linlin Shen
Breast cancer is the second most common malignancy among women and has become a major public health problem in current society. Traditional breast cancer identification requires ex…
Skin Lesion Analysis Towards Melanoma Detection Using Deep Learning Network
Yuexiang Li, Linlin Shen
Skin lesion is a severe disease in world-wide extent. Early detection of melanoma in dermoscopy images significantly increases the survival rate. However, the accurate recognition…