AI Paper Atlas

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

SOTA: Self-adaptive Optimal Transport for Zero-Shot Classification with Multiple Foundation Models

Zhanxuan Hu, Qiyu Xu, Yu Duan, Yonghang Tai, Huafeng Li

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 1 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 vision-only foundation models (DINO) to the VLM ensemble (ablation)SOTA · natural, remote sensing, medical (ablation average)top-1 accuracy (%): +11.1 / +8.6 / +12.9 over base (full SOTA)Improved
integrate multiple VLMs only (Only-P-hat), no VFM (ablation)SOTA · natural, remote sensing, medical (ablation average)top-1 accuracy (%): +0.2 / +0.3 / +0.8Improved
use self-adaptive weights instead of fixed weights (ablation)SOTA · natural, remote sensing, medical (ablation average)top-1 accuracy (%): modest improvementImproved
use self-adaptive weights instead of non-adaptive weights with CLIP and MUSK (ablation)SOTA · 5 medical datasets (CLIP+MUSK)average top-1 accuracy (%): 71.8 -> 73.1Improved
use joint learning of GMM and transport plan instead of disjoint learning (ablation)SOTA · natural, remote sensing, medical (ablation average)top-1 accuracy (%)Improved
swap CLIP ViT-B/16 for a stronger visual encoder (DINOv3) in the ensembleSOTA · 11 natural datasets, transductiveaverage top-1 accuracy (%): 72.5 -> 77.4Improved
add DINOv2 and DINOv3 jointly versus DINOv3 aloneSOTA · 11 natural datasets, transductiveaverage top-1 accuracy (%): 77.4 -> 77.8No clear effect
ensemble two CLIP variants (ViT-B/16 + RN50) on AircraftSOTA · Aircraft, transductiveaccuracy (%): 24.7 -> 22.6Hurt
ensemble four pathology/general VLMs with SOTA instead of applying TransCLIP to the best modelSOTA · 5 medical pathology datasets, transductiveaverage top-1 accuracy (%): 76.0 -> 83.9Improved
ensemble four remote sensing VLMs with SOTA instead of applying TransCLIP to the best modelSOTA · 10 remote sensing datasets, transductiveaverage top-1 accuracy (%): 76.2 -> 81.5Improved
use SOTA in inductive mode versus test-time adaptation methodsSOTA · 11 natural datasets, inductiveaverage top-1 accuracy (%): 73.3 -> 77.6Improved

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