activity
20242026
collaborators

5 papers

cs.CV2026

Weakly Supervised Incremental Segmentation via Semantic Anchors and Spatial Arbitration

Zhonggai Wang, Kai Fang, Guangyu Gao

Weakly Incremental Learning for Semantic Segmentation (WILSS) suffers from the continuous introduction of noisy supervision, which progressively corrupts class-level representation…

cs.CV2026

FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation

Zekang Zhang, Guangyu Gao, Youyun Tang +7

LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mo…

cs.CV2026

Rethinking MLLM Itself as a Segmenter with a Single Segmentation Token

Anqi Zhang, Xiaokang Ji, Guangyu Gao +3

Recent segmentation methods leveraging Multi-modal Large Language Models (MLLMs) have shown reliable object-level segmentation and enhanced spatial perception. However, almost all…

cs.CV2025

CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation

Kai Fang, Anqi Zhang, Guangyu Gao +3

Effective Class Incremental Segmentation (CIS) requires simultaneously mitigating catastrophic forgetting and ensuring sufficient plasticity to integrate new classes. The inherent…

cs.CV2024

Bridge the Points: Graph-based Few-shot Segment Anything Semantically

Anqi Zhang, Guangyu Gao, Jianbo Jiao +2

The recent advancements in large-scale pre-training techniques have significantly enhanced the capabilities of vision foundation models, notably the Segment Anything Model (SAM), w…