AI Paper Atlas

Research map / Continual learning / Class-incremental

Forget What Has Seen: Selective Concept Unlearning in Segmentation Foundation Models

Miaozeng Du, Jiaqi Li, Sirui Pan, Yi Zhan, Guilin Qi, Yuxin Zhang, Rihui Jin, Yinjia Shu, Qianshan Wei

AAAI 2026 · Continual learning › Class-incremental · approach: Unknown-class mining for incremental segmentation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add negative distillation level (ablation)SCU · SAM1 concept unlearning (8 concepts)Efficacy IoU (lower better): 32.8 -> 16.3Improved
add attention-level suppression (ablation)SCU · SAM1 concept unlearning (8 concepts)Efficacy IoU (lower better): 26.5 -> 16.3Improved
add output-level relabeling (ablation)SCU · SAM1 concept unlearning (8 concepts)Efficacy IoU (lower better): 27.9 -> 16.3Improved
add output-level relabeling (ablation)SCU · SAM1 concept unlearning (8 concepts)Specificity IoU: 32.5 -> 61.3Improved
add Preservation Module (ablation)SCU · SAM1 concept unlearning (8 concepts)Specificity IoU: 21.4 -> 61.3Improved
add Preservation Module (ablation)SCU · SAM1 concept unlearning (8 concepts)Efficacy IoU (lower better): 17.6 -> 16.3No clear effect
use SCU instead of Gradient AscentSCU · SAM1 concept unlearningSpecificity IoU: 16.1 -> 61.3Improved
use SCU instead of Boundary Shrink / Random Labeling / Boundary ExpandSCU · SAM1 concept unlearningEfficacy IoU (lower better): 63.4 -> 16.3 (vs RL)Improved
use SCU instead of L1-sparseSCU · SAM1 concept unlearningNormalized Score: 0.723 -> 0.923Improved
use SCU on SAM2 instead of SAM1SCU · SCU, SAM1 vs SAM2Normalized Score: 0.923 -> 0.929No clear effect
increase unlearning training stepsSCU · SAM1 steps sweepSpecificity: SCU stable; GA and RL dropImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy