64 citations · 115 across the 15 of their papers we have counts for
15 papers
SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation
Chunming He, Rihan Zhang, Longxiang Tang +4
Existing methods for label-deficient concealed object segmentation (LDCOS) either rely on consistency constraints or Segment Anything Model (SAM)-based pseudo-labeling. However, th…
Segment Concealed Objects with Incomplete Supervision
Chunming He, Kai Li, Yachao Zhang +8
Incompletely-Supervised Concealed Object Segmentation (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments, utilizing incompletely annotate…
RUN: Reversible Unfolding Network for Concealed Object Segmentation
Chunming He, Rihan Zhang, Fengyang Xiao +7
Existing concealed object segmentation (COS) methods frequently utilize reversible strategies to address uncertain regions. However, these approaches are typically restricted to th…
InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
Chenyang Zhu, Kai Li, Yue Ma +5
Recent advances in Customized Concept Swapping (CCS) enable a text-to-image model to swap a concept in the source image with a customized target concept. However, the existing meth…
Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models
Longxiang Tang, Zhuotao Tian, Kai Li +5
This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes va…
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
Chengyu Fang, Chunming He, Fengyang Xiao +5
Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real…
MultiBooth: Towards Generating All Your Concepts in an Image from Text
Chenyang Zhu, Kai Li, Yue Ma +2
This paper introduces MultiBooth, a novel and efficient technique for multi-concept customization in image generation from text. Despite the significant advancements in customized…
Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
Chunming He, Chengyu Fang, Yulun Zhang +6
Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among t…
Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
Chunming He, Kai Li, Yachao Zhang +5
Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. Albeit achieving remarkable success, existing COD…
Consistency Regularization for Generalizable Source-free Domain Adaptation
Longxiang Tang, Kai Li, Chunming He +2
Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variet…
HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance
Chunming He, Kai Li, Guoxia Xu +5
Unpaired Medical Image Enhancement (UMIE) aims to transform a low-quality (LQ) medical image into a high-quality (HQ) one without relying on paired images for training. While most…
Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher
Longxiang Tang, Kai Li, Chunming He +2
This paper studies source-free domain adaptive fundus image segmentation which aims to adapt a pretrained fundus segmentation model to a target domain using unlabeled images. This…
Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping
Chunming He, Kai Li, Yachao Zhang +5
Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It rema…
Towards Realizing the Value of Labeled Target Samples: a Two-Stage Approach for Semi-Supervised Domain Adaptation
mengqun Jin, Kai Li, Shuyan Li +2
Semi-Supervised Domain Adaptation (SSDA) is a recently emerging research topic that extends from the widely-investigated Unsupervised Domain Adaptation (UDA) by further having a fe…
Adversarial Alignment for Source Free Object Detection
Qiaosong Chu, Shuyan Li, Guangyi Chen +2
Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data. While most exist…