collaborators

10 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…