AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

SAMPLe: A Sharpness Aware Minimization based Optimizer for Prompt Learning in Vision-Language Models

Hossein Rajoli nowdeh, Fatemeh Lotfi, Niloufar Alipour Talemi, Hossein Kashiani, Xiaolong Ma, Fatemeh Afghah

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 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 SAMPLe optimizer to CoOpCoOp · Base-to-new, 11-dataset avgHM: 77.65 -> 78.88 (vs SAGM); 71.66 baselineImproved
add SAMPLe optimizer to CoCoOpCoCoOp · Base-to-new, 11-dataset avgHM: 78.28 -> 79.51 (vs SAGM)Improved
add SAMPLe optimizer to MaPLeMaPLe · Base-to-new, 11-dataset avgHM: 79.96 -> 80.28 (vs SAGM)Improved
add SAMPLe optimizer to CoPromptCoPrompt · Base-to-new, 11-dataset avgHM: 81.49 -> 82.02 (vs SAGM)Improved
add SAMPLe optimizer to TCPTCP · Base-to-new, 11-dataset avgHM: 81.40 -> 81.95 (vs SAGM)Improved
add SAMPLe optimizer to CoOpCoOp · Cross-dataset zero-shotavg accuracy: 63.88 -> 65.85Improved
add SAMPLe optimizer to TCPTCP · Cross-dataset zero-shotavg accuracy: 66.29 -> 67.53Improved
add SAMPLe optimizer to CoOpCoOp · Domain generalizationavg accuracy: 59.28 -> 60.41Improved
add SAMPLe optimizer to TCPTCP · Domain generalizationavg accuracy: 60.51 -> 61.90Improved
add SAMPLe to CoOp on source ImageNet accuracyCoOp · Domain generalization (source ImageNet)accuracy: 71.51 -> 70.60Hurt
add FSAM to CoOp on ImageNet base-to-newCoOp · Base-to-new, ImageNetbase accuracy: 76.47 -> 69.79Hurt
add gradient-alignment term to SAM objective (L + Lp - alpha grad.grad) (ablation)CoPrompt · Base-to-new, 11-dataset avgHM: 80.99 -> 81.49Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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