AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection

Ruoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Li Liu, Hua Zhang, Xiaochun Cao

TPAMI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods · 10 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
use SLICO superpixel division instead of Segment Anything (ablation)LiMA · ImageNet val, CLIP (ViT-L)Insertion AUC: 0.7151 -> 0.7441Improved
use SLICO superpixel division instead of Segment Anything (ablation)LiMA · ImageNet val, CLIP (ViT-L)Deletion AUC: 0.1905 -> 0.0926Improved
use SLICO division instead of SAM (ablation)LiMA · CUB-200-2011 valInsertion AUC: 0.7106 -> 0.7748Improved
use SLICO division instead of SAM (ablation)LiMA · ImageNet val, LanguageBindInsertion AUC: 0.6690 -> 0.6058Hurt
replace previous ICLR version with semantic-division LiMA (SAM)LiMA · ImageNet val, CLIP (ViT-L)Insertion AUC: 0.6752 -> 0.7151Improved
replace RISE with LiMA (SLICO)LiMA · ImageNet val, ViT-LInsertion AUC: 0.6177 -> 0.7405Improved
replace RISE with LiMA (SLICO)LiMA · ImageNet val, MambaVision (L2)Insertion AUC: 0.2937 -> 0.3680Improved
replace HSIC-Attribution with LiMA (SLICO)LiMA · ImageNet val, LanguageBindmuFidelity: 0.4132 -> 0.4096Hurt
replace HSIC-Attribution with LiMA (SLICO)LiMA · ImageNet val, ResNet-101muFidelity: 0.5805 -> 0.4203Hurt
replace HSIC-Attribution with LiMA (SLICO)LiMA · Celeb-ADeletion AUC: 0.1151 -> 0.0668Improved
use bidirectional greedy search instead of standard forward ranking (ablation)LiMA · ImageNet default N=49candidate evaluations: 1,225 -> 805Improved

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