224 citations · 538 across the 25 of their papers we have counts for
30 papers
Seeing Through the Glare: A Multi-Source Benchmark and Ocular-Adaptive Pixel MeanFlow for Eyeglass Reflection Removal
Tao Liu, Youwei Pang, Kailai Zhou +7
Eyeglass reflection removal is important across smartphone imaging, video conferencing, and other face-centric visual applications. The task is challenging because reflections rang…
Hard, Yet Reducible: Controlled Forward Transfer for Synthetic Degradation Curation
Chunming He, Kailai Zhou, Jiaming Zuo +6
Selecting synthetic degradations for dense prediction requires an estimate of their training utility, the generalization gain they bring under a finite training budget. Clean and d…
Beyond Pixel Overlap: A Framework for Decomposing Segmentation Evaluation Metrics
Youwei Pang, Xiaoqi Zhao
Evaluation metrics are central to binary target segmentation because they determine how progress is measured, compared, and interpreted. In this paper, target denotes the task-defi…
Towards Large Model Feature Coding
Youwei Pang, Changsheng Gao, Dong Liu +2
Large models have delivered remarkable performance across a wide range of perception and generation tasks, yet practical deployment is increasingly constrained by computational and…
ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning
Yuan Zhao, Youwei Pang, Jiaming Zuo +10
Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the notion of a concept remains…
Rethinking Evaluation of Infrared Small Target Detection
Youwei Pang, Xiaoqi Zhao, Lihe Zhang +4
As an essential vision task, infrared small target detection (IRSTD) has seen significant advancements through deep learning. However, critical limitations in current evaluation pr…
UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation
Xiaoqi Zhao, Youwei Pang, Chenyang Yu +5
Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance. While existing methods address training-inference…
UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompression
Yuan Zhao, Youwei Pang, Lihe Zhang +4
Existing anomaly detection (AD) methods often treat the modality and class as independent factors. Although this paradigm has enriched the development of AD research branches and p…
Power Battery Detection
Xiaoqi Zhao, Peiqian Cao, Chenyang Yu +10
Power batteries are essential components in electric vehicles, where internal structural defects can pose serious safety risks. We conduct a comprehensive study on a new task, powe…
Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
Xiaoqi Zhao, Youwei Pang, Shijie Chang +10
As large-scale foundation models trained on billions of image--mask pairs covering a vast diversity of scenes, objects, and contexts, SAM and its upgraded version, SAM~2, have sign…
Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation
Shijie Chang, Youwei Pang, Xiaoqi Zhao +2
Existing few-shot segmentation (FSS) methods mainly focus on prototype feature generation and the query-support matching mechanism. As a crucial prompt for generating prototype fea…
Spider: A Unified Framework for Context-dependent Concept Segmentation
Xiaoqi Zhao, Youwei Pang, Wei Ji +4
Different from the context-independent (CI) concepts such as human, car, and airplane, context-dependent (CD) concepts require higher visual understanding ability, such as camoufla…
Multi-view Aggregation Network for Dichotomous Image Segmentation
Qian Yu, Xiaoqi Zhao, Youwei Pang +2
Dichotomous Image Segmentation (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. When designing an effective DIS model, the…
Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline
Xiaoqi Zhao, Youwei Pang, Zhenyu Chen +5
We conduct a comprehensive study on a new task named power battery detection (PBD), which aims to localize the dense cathode and anode plates endpoints from X-ray images to evaluat…
Open-Vocabulary Camouflaged Object Segmentation
Youwei Pang, Xiaoqi Zhao, Jiaming Zuo +2
Recently, the emergence of the large-scale vision-language model (VLM), such as CLIP, has opened the way towards open-world object perception. Many works have explored the utilizat…
ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang +2
Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Ap…
ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer
Youwei Pang, Xiaoqi Zhao, Lihe Zhang +1
Deep learning (DL) has advanced the field of dense prediction, while gradually dissolving the inherent barriers between different tasks. However, most existing works focus on desig…
MSNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation
Xiaoqi Zhao, Hongpeng Jia, Youwei Pang +5
Accurate medical image segmentation is critical for early medical diagnosis. Most existing methods are based on U-shape structure and use element-wise addition or concatenation to…
Towards Diverse Binary Segmentation via A Simple yet General Gated Network
Xiaoqi Zhao, Youwei Pang, Lihe Zhang +2
In many binary segmentation tasks, most CNNs-based methods use a U-shape encoder-decoder network as their basic structure. They ignore two key problems when the encoder exchanges i…
Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation
Xiaoqi Zhao, Shijie Chang, Youwei Pang +3
Static and moving objects often occur in real-life videos. Most video object segmentation methods only focus on extracting and exploiting motion cues to perceive moving objects. On…
Few-Shot Segmentation via Rich Prototype Generation and Recurrent Prediction Enhancement
Hongsheng Wang, Xiaoqi Zhao, Youwei Pang +1
Prototype learning and decoder construction are the keys for few-shot segmentation. However, existing methods use only a single prototype generation mode, which can not cope with t…
Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection
Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang +2
The recently proposed camouflaged object detection (COD) attempts to segment objects that are visually blended into their surroundings, which is extremely complex and difficult in…
Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction
Xiaoqi Zhao, Youwei Pang, Lihe Zhang +1
Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extractin…
CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
Youwei Pang, Xiaoqi Zhao, Lihe Zhang +1
Most of the existing bi-modal (RGB-D and RGB-T) salient object detection methods utilize the convolution operation and construct complex interweave fusion structures to achieve cro…