AI Paper Atlas

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

Towards Calibrating Prompt Tuning of Vision- Language Models

Ashshak Sharifdeen, Fahad Shamshad, Muhammad Akhtar Munir, Abhishek Basu, Mohamed Ismithdeen, Jeyapriyan Jeyamohan, Chathurika Silva, Karthik Nandakumar, Muhammad Haris Khan

CVPR 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 mean-variance margin regularization to cross-entropy (ablation)MaPLe · novel classes, avg ECEECE (%): 5.76 -> 5.09Improved
add moment-matching loss on top of margin regularization (ablation)MaPLe · novel classes, avg ECEECE (%): 5.09 -> 4.48Improved
add direct L1 embedding alignment to margin loss (instead of moment matching) (ablation)MaPLe · novel classes, avg ECEECE (%): 5.09 -> 5.17; accuracy 75.74 -> 74.65No clear effect
add margin and moment-matching regularizersCoOp · base classes, avg ECEECE (%): 6.35 -> 2.93Improved
add margin and moment-matching regularizersMaPLe · base classesECE (%) and accuracy (%): ECE 3.19 -> 2.78; accuracy 82.41 -> 82.75Improved
add margin and moment-matching regularizersMaPLe · novel classes, avg ECEECE (%): 5.76 -> 4.23Improved
add margin and moment-matching regularizersCoOp · novel classes, avg ECEECE (%): 12.45 -> 4.79Improved
add margin and moment-matching regularizersKgCoOp · base classes, avg ECEECE (%): 6.02 -> 5.47Improved
add margin and moment-matching regularizersKgCoOp · novel classes, avg ECEECE (%): 3.71 -> 3.33Improved
add margin and moment-matching regularizersCoOp · Aircraft base classesECE (%): 25.70 -> 4.96Improved
apply temperature scaling post hoc instead of train-time regularizationCoOp · base classes, avg ECEECE (%): 6.35 -> 2.96Improved
apply MBLS label smoothing baselineCoOp · base classes, avg ECEECE (%): 6.35 -> 9.04Hurt

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