AI Paper Atlas

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

SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning

Leo Fillioux, Omprakash Chakraborty, Ismail Ben Ayed, Paul-Henry Cournède, Stergios Christodoulidis, Maria Vakalopoulou, Jose Dolz

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 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
replace full orthogonality penalty (O-TPT) with Huber regularizer (SoC)TPT · Average of 11 datasets (ViT-L/14)ECE: 7.7 -> 5.4Improved
replace full orthogonality penalty with Huber regularizerTPT · Average of 11 datasets (ViT-L/14)accuracy: 71.4 -> 72.3Improved
replace full orthogonality penalty with Huber regularizerTPT · EuroSATECE: 17.7 -> 3.2Improved
replace full orthogonality penalty with Huber regularizerTPT · ImageNetECE: 5.5 -> 7.2Hurt
replace full orthogonality penalty with Huber regularizerTPT · Average of 11 datasets (ViT-B/16)ECE: 4.8 -> 4.3Improved
replace full orthogonality penalty with Huber regularizerTPT · ImageNet variants averageECE: 9.9 -> 8.4Improved
replace full orthogonality penalty with Huber regularizerTPT · ImageNet variants averageaccuracy: 71.3 -> 71.3No clear effect
add a second gradient update on text prompts (ablation)SoC vs O-TPT · Average of 11 datasetsECE: SoC degraded nearly 23%; O-TPT 39%Hurt
replace full orthogonality penalty with Huber regularizer under two gradient updatesTPT · Average of 11 datasetsECE: 10.8 -> 6.6Improved
replace full orthogonality penalty with Huber regularizer with CoOp 4-shot promptsTPT+CoOp · Average of 11 datasetsaccuracy: 76.6 -> 78.0Improved
normalize similarities with min-max (S1) instead of dividing by max (S2) (ablation)SoC · Average of 8 datasetsaccuracy and ECE: accuracy 70.7 -> 70.3; ECE 7.3 -> 5.3Mixed
normalize similarities with min-max (S1) instead of subtracting min (S3) (ablation)SoC · Average of 8 datasetsaccuracy: 69.2 -> 70.3Improved

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