85 citations · 273 across the 108 of their papers we have counts for
21 papers · 1 filter
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…
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…
GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance
Haiming Zhang, Zhihao Yuan, Chaoda Zheng +6
Although existing speech-driven talking face generation methods achieve significant progress, they are far from real-world application due to the avatar-specific training demand an…
Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training
Runze He, Shaofei Huang, Xuecheng Nie +6
In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt…
FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
Jichang Li, Guanbin Li, Hui Cheng +2
Federated learning with noisy labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning by aggregating multiple client models trained with local…
Open-Vocabulary Segmentation with Semantic-Assisted Calibration
Yong Liu, Sule Bai, Guanbin Li +2
This paper studies open-vocabulary segmentation (OVS) through calibrating in-vocabulary and domain-biased embedding space with generalized contextual prior of CLIP. As the core of…
Prompt-based Grouping Transformer for Nucleus Detection and Classification
Junjia Huang, Haofeng Li, Weijun Sun +2
Automatic nuclei detection and classification can produce effective information for disease diagnosis. Most existing methods classify nuclei independently or do not make full use o…
Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection
Junjia Huang, Haofeng Li, Xiang Wan +1
Multi-class cell nuclei detection is a fundamental prerequisite in the diagnosis of histopathology. It is critical to efficiently locate and identify cells with diverse morphology…
Diffusion-based Data Augmentation for Nuclei Image Segmentation
Xinyi Yu, Guanbin Li, Wei Lou +4
Nuclei segmentation is a fundamental but challenging task in the quantitative analysis of histopathology images. Although fully-supervised deep learning-based methods have made sig…
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Pengxu Wei, Yujing Sun, Xingbei Guo +4
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especial…
MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization
Tao Chen, Ze Lin, Hui Li +4
Given the long textual product information and the product image, Multi-modal Product Summarization (MPS) aims to increase customers' desire to purchase by highlighting product cha…
YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection
Yuncheng Jiang, Zixun Zhang, Ruimao Zhang +3
Accurate polyp detection is essential for assisting clinical rectal cancer diagnoses. Colonoscopy videos contain richer information than still images, making them a valuable resour…
Divide and Adapt: Active Domain Adaptation via Customized Learning
Duojun Huang, Jichang Li, Weikai Chen +3
Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target s…
Advancing Visual Grounding with Scene Knowledge: Benchmark and Method
Zhihong Chen, Ruifei Zhang, Yibing Song +2
Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understand…
Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation
Zunnan Xu, Zhihong Chen, Yong Zhang +3
Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few st…
Universal Semi-supervised Model Adaptation via Collaborative Consistency Training
Zizheng Yan, Yushuang Wu, Yipeng Qin +3
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained sou…
SCoDA: Domain Adaptive Shape Completion for Real Scans
Yushuang Wu, Zizheng Yan, Ce Chen +6
3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing…
Structure Embedded Nucleus Classification for Histopathology Images
Wei Lou, Xiang Wan, Guanbin Li +4
Nuclei classification provides valuable information for histopathology image analysis. However, the large variations in the appearance of different nuclei types cause difficulties…
Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts
Zhihong Chen, Shizhe Diao, Benyou Wang +2
Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representation…
Lesion-aware Dynamic Kernel for Polyp Segmentation
Ruifei Zhang, Peiwen Lai, Xiang Wan +4
Automatic and accurate polyp segmentation plays an essential role in early colorectal cancer diagnosis. However, it has always been a challenging task due to 1) the diverse shape,…
Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation
Ruifei Zhang, Sishuo Liu, Yizhou Yu +1
Biomedical image segmentation plays a significant role in computer-aided diagnosis. However, existing CNN based methods rely heavily on massive manual annotations, which are very e…