Weakly Supervised Incremental Segmentation via Semantic Anchors and Spatial Arbitration
Quick Take
The SASA approach enhances weakly supervised incremental learning for semantic segmentation by using Semantic Anchors and Spatial Arbitration to mitigate feature drift and improve supervision reliability, outperforming existing methods in multi-step incremental settings.
Key Points
- SASA introduces learnable semantic anchors to stabilize class-level representations.
- Elastic residual adaptation allows for instance-specific refinement in learning.
- Spatial Label Arbitration filters unreliable signals and enforces strict class constraints.
- Extensive experiments show SASA outperforms state-of-the-art methods on standard benchmarks.
- Code for SASA is available on GitHub for further research.
Article Content
From source RSS / original summaryarXiv: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 approach, named SASA, designed to stabilize semantic learning via Semantic Anchors and Spatial Arbitration.
Specifically, at the representation level, we introduce semantic anchors of learnable tokens as rigid class-level references to preserve long-term semantic identity. Complementary to this, an elastic residual adaptation facilitates controlled, instance-specific refinement, ensuring a stable yet flexible learning trajectory.
At the supervision level, we develop a Spatial Label Arbitration mechanism that performs geometry-aware decisions to directly filter unreliable signals and enforce a strict "one object, one class" constraint. By synergistically stabilizing representations and improving supervision reliability, SASA effectively mitigates feature drift under weak supervision.
Extensive experiments on standard benchmarks demonstrate that our approach consistently outperforms existing state-of-the-art methods, particularly in challenging multi-step incremental settings. The code is available at https://github. com/ZhonggaiWang/SASA.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Optimal Transport Flow Matching by Design
The study presents a novel approach to optimal transport (OT) flow matching, reformulating the problem by treating the prior as a design choice. This method achieves over 2x reduction in trajectory curvature compared to existing methods, improving generation quality in few-step regimes without altering the flow model. The approach integrates seamlessly with latent-space models and classifier-free guidance.