Publications (37)
Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation
Lechao Cheng, Zerun Liu, Jingxuan He +3
Weakly supervised semantic segmentation (WSSS) has recently attracted considerable attention because it requires fewer annotations than fully supervised approaches, making it espec…
Revisiting the Power of Prompt for Visual Tuning
Yuzhu Wang, Lechao Cheng, Chaowei Fang +3
Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often e…
Combating Noisy Labels in Long-Tailed Image Classification
Chaowei Fang, Lechao Cheng, Huiyan Qi +1
Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenario…
A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-Resolution
Hongying Liu, Zhubo Ruan, Chaowei Fang +4
Spherical videos, also known as \ang{360} (panorama) videos, can be viewed with various virtual reality devices such as computers and head-mounted displays. They attract large amou…
Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal
Yicheng Leng, Chaowei Fang, Junye Chen +3
Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DN…
Progressive Conservative Adaptation for Evolving Target Domains
Gangming Zhao, Chaoqi Chen, Wenhao He +5
Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. However, in many real-world cases, target data usually emerge seque…
Computer-aided Tuberculosis Diagnosis with Attribute Reasoning Assistance
Chengwei Pan, Gangming Zhao, Junjie Fang +6
Although deep learning algorithms have been intensively developed for computer-aided tuberculosis diagnosis (CTD), they mainly depend on carefully annotated datasets, leading to mu…
Diffusion Masked Pretraining for Dynamic Point Cloud
Zhuoyue Zhang, Jihua Zhu, Chaowei Fang +2
Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing methods inject ground-truth…
MVCNet: Multiview Contrastive Network for Unsupervised Representation Learning for 3D CT Lesions
Penghua Zhai, Huaiwei Cong, Gangming Zhao +4
\emph{Objective and Impact Statement}. With the renaissance of deep learning, automatic diagnostic systems for computed tomography (CT) have achieved many successful applications.…
Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal
Yicheng Leng, Chaowei Fang, Gen Li +2
Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Vi…
Piecewise Flat Embedding for Image Segmentation
Chaowei Fang, Zicheng Liao, Yizhou Yu
We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation. Based on the theory of sparse signal recovery, piecewise flat…
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
Dingwen Zhang, Wenyuan Zeng, Guangyu Guo +4
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model. These approaches wo…
Deep Transformers for Fast Small Intestine Grounding in Capsule Endoscope Video
Xinkai Zhao, Chaowei Fang, Feng Gao +3
Capsule endoscopy is an evolutional technique for examining and diagnosing intractable gastrointestinal diseases. Because of the huge amount of data, analyzing capsule endoscope vi…
Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation
Chaowei Fang, Guanbin Li, Chengwei Pan +2
Recently 3D volumetric organ segmentation attracts much research interest in medical image analysis due to its significance in computer aided diagnosis. This paper aims to address…
Variance-insensitive and Target-preserving Mask Refinement for Interactive Image Segmentation
Chaowei Fang, Ziyin Zhou, Junye Chen +3
Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. However, fully extracting the tar…
Deep 3D Vessel Segmentation based on Cross Transformer Network
Chengwei Pan, Baolian Qi, Gangming Zhao +4
The coronary microvascular disease poses a great threat to human health. Computer-aided analysis/diagnosis systems help physicians intervene in the disease at early stages, where 3…
Contralaterally Enhanced Networks for Thoracic Disease Detection
Gangming Zhao, Chaowei Fang, Guanbin Li +2
Identifying and locating diseases in chest X-rays are very challenging, due to the low visual contrast between normal and abnormal regions, and distortions caused by other overlapp…
Cross-Modality High-Frequency Transformer for MR Image Super-Resolution
Chaowei Fang, Dingwen Zhang, Liang Wang +3
Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis. Higher resolution helps to capture more detailed…
Meta Corrupted Pixels Mining for Medical Image Segmentation
Jixin Wang, Sanping Zhou, Chaowei Fang +2
Deep neural networks have achieved satisfactory performance in piles of medical image analysis tasks. However the training of deep neural network requires a large amount of samples…
Self-Enhanced Convolutional Network for Facial Video Hallucination
Chaowei Fang, Guanbin Li, Xiaoguang Han +1
As a domain-specific super-resolution problem, facial image hallucination has enjoyed a series of breakthroughs thanks to the advances of deep convolutional neural networks. Howeve…
Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
Fangwen Wu, Lechao Cheng, Shengeng Tang +4
Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones. Balancing flexibility and stability…
Dual-domain Adaptation Networks for Realistic Image Super-resolution
Chaowei Fang, Bolin Fu, De Cheng +2
Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones, handling more complex degradation patterns than…
Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics
Chaowei Fang, Dingwen Zhang, Wen Zheng +4
Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are de…
Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image Segmentation
Xinkai Zhao, Chaowei Fang, De-Jun Fan +3
Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of…
PNEN: Pyramid Non-Local Enhanced Networks
Feida Zhu, Chaowei Fang, Kai-Kuang Ma
Existing neural networks proposed for low-level image processing tasks are usually implemented by stacking convolution layers with limited kernel size. Every convolution layer mere…
Graph Neural Networks for UnsupervisedDomain Adaptation of Histopathological ImageAnalytics
Dou Xu, Chang Cai, Chaowei Fang +3
Annotating histopathological images is a time-consuming andlabor-intensive process, which requires broad-certificated pathologistscarefully examining large-scale whole-slide images…
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
Ying Yang, De Cheng, Chaowei Fang +4
Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is crucial for dev…
Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis
Chaowei Fang, Liang Wang, Dingwen Zhang +3
Due to the constraints of the imaging device and high cost in operation time, computer tomography (CT) scans are usually acquired with low intra-slice resolution. Improving the int…
Densely Nested Top-Down Flows for Salient Object Detection
Chaowei Fang, Haibin Tian, Dingwen Zhang +3
With the goal of identifying pixel-wise salient object regions from each input image, salient object detection (SOD) has been receiving great attention in recent years. One kind of…
Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning
Junkai Huang, Chaowei Fang, Weikai Chen +5
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. Whil…
Progressive Feature Self-reinforcement for Weakly Supervised Semantic Segmentation
Jingxuan He, Lechao Cheng, Chaowei Fang +3
Compared to conventional semantic segmentation with pixel-level supervision, Weakly Supervised Semantic Segmentation (WSSS) with image-level labels poses the challenge that it alwa…
Tri-Efficient Transfer Learning for Point Cloud Videos
Yiding Sun, Dongxu Zhang, Jihua Zhu +6
While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two criti…
Identity-Preserving Talking Face Generation with Landmark and Appearance Priors
Weizhi Zhong, Chaowei Fang, Yinqi Cai +4
Generating talking face videos from audio attracts lots of research interest. A few person-specific methods can generate vivid videos but require the target speaker's videos for tr…
Compound Batch Normalization for Long-tailed Image Classification
Lechao Cheng, Chaowei Fang, Dingwen Zhang +2
Significant progress has been made in learning image classification neural networks under long-tail data distribution using robust training algorithms such as data re-sampling, re-…
WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning
Dongjian Huo, Zehong Zhang, Hanjing Su +3
Watermarking serves as a widely adopted approach to safeguard media copyright. In parallel, the research focus has extended to watermark removal techniques, offering an adversarial…
Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP
Yuhang Huang, Chenmiao Li, Chaowei Fang
Many games rely on storytelling combined with systems that track levelling, NPC behaviour, and consequence simulation; bridging tightly-authored narrative with deeply-simulated wor…
PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning
Dongxu Zhang, Yiding Sun, Pengcheng Li +12
While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant c…