Weakly Supervised Incremental Segmentation via Semantic Anchors and Spatial Arbitration 事件

Weakly Supervised Incremental Segmentation via Semantic Anchors and Spatial Arbitration arXiv:2606.04060v1 Announce Type: new Abstract: Weakly Incremental Learning for Semantic Segmentation (WILSS) suffers from the continuous introduction of noisy supervision, which progressively corrupts class-level representations, leading to severe feature drift and semantic corruption, thereby causing newly learned classes to overwrite old ones. To address these issues, we propose a drift-resilient WILSS ap