AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Segment Anything with Robust Uncertainty-Accuracy Correlation

Hongyou Zhou, Marc Toussaint, Ling Shao, Zihan Ye

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 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 Bayesian uncertainty estimation decoderSAM2-FT · Zero-shot DG, 23 datasetsJ&F avg: 79.75 -> 79.87No clear effect
add adversarial uncertainty estimation (style + deform) to Bayes-SAM2 (ablation)Bayes-SAM2 · Zero-shot DG, 23 datasetsJ&F avg: 79.87 -> 81.62Improved
add deformation attack to style-GCN attack (ablation)RUAC-Style-GCN · Zero-shot DGJ&F avg: 80.74 -> 81.62Improved
add style attack to deformation-only attack (ablation)RUAC-Deform · Zero-shot DGJ&F avg: 80.44 -> 81.62Improved
add GCN refinement to multi-object style attack (ablation)RUAC-Style-Multi · Zero-shot DGJ&F avg: 80.52 -> 80.74Improved
add background to multi-object style perturbation (ablation)RUAC-Style-Multi · Zero-shot DGJ&F avg: 80.52 -> 80.68Improved
perturb multiple objects instead of target only (ablation)RUAC-Style-Single · Zero-shot DGJ&F avg: 80.43 -> 80.52Improved
replace global style perturbation with per-object style (ablation)RUAC-Style-Global · Zero-shot DGJ&F avg: 80.26 -> 80.52Improved
add adversarial uncertainty estimation (ablation)Bayes-SAM2 · OOD calibrationPAvPU: 55.40 -> 63.72Improved
add adversarial uncertainty estimation (ablation)Bayes-SAM2 · In-domain MOSEPAvPU: 86.9 -> 81.6Hurt
add adversarial uncertainty estimation (ablation)Bayes-SAM2 · OOD calibrationECE: 0.123 -> 0.117Improved
apply uncertainty-guided correction filterRUAC · 23 OOD datasetsJ&F: 81.62 -> 81.71Improved

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