AI Paper Atlas

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

Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting

Alexey Kravets, Da Chen, Vinay P. Namboodiri

ICCV 2025 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 2 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
unlearn benchmark classes from CLIP (inductive evaluation)CoOp · 7 datasets avg, inductive (unlearned CLIP)accuracy: 71.4 -> 15.3Hurt
unlearn benchmark classes from CLIP (inductive evaluation)PromptSRC · 7 datasets avg, inductive (unlearned CLIP)accuracy: 74.7 -> 20.1Hurt
unlearn benchmark classes from CLIP (inductive evaluation)CLIPLora · 7 datasets avg, inductive (unlearned CLIP)accuracy: 74.9 -> 19.2Hurt
unlearn benchmark classes from CLIP (inductive evaluation)SEPRES · 7 datasets avg, inductive (unlearned CLIP)accuracy: 75.4 -> 56Hurt
add residual textual features to SEP (RES) (ablation)SEP · 7 datasets avg, inductive (unlearned CLIP)accuracy: 11.511 -> 56.428Improved
add SEP to residual features (ablation)only RES · 7 datasets avg, inductive (unlearned CLIP)accuracy: 21.492 -> 56.428Improved
add visual residual features (vRES) (ablation)SEPRES · 7 datasets avg, inductive (unlearned CLIP)accuracy: 56.428 -> 56.17No clear effect
set residual weight alpha to 0 (no residual features) (ablation)SEPRES · inductive and partially transductiveaccuracyHurt
increase residual weight alpha from 0.1 towards 1 (ablation)SEPRES · partially transductiveaccuracyHurt
use SSD unlearning instead of SalUn (ablation)CLIP unlearning · Unlearning Dogs, Cars, Flowersavg knowledge lost: 0.3617 -> 0.0283Improved
use SSD unlearning instead of TextProj (ablation)CLIP unlearning · Unlearning Dogs, Cars, Flowersavg knowledge lost: 0.0967 -> 0.0283Improved
unlearn subset vs train CLIP without the subset (ablation)CLIP oracle · Birds subset accuracyaccuracy on subset: 0.043 vs 0.082No clear effect

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