AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

BATCLIP: Bimodal Online Test-Time Adaptation for CLIP

Sarthak Maharana, Baoming Zhang, Leonid Karlinsky, Rogerio Feris, Yunhui Guo

ICCV 2025 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 18 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 inter-class separability loss L_sp to entropy minimization (ablation)BATCLIP (ViT-B/16) · CIFAR-10Cmean accuracy: 60.65 -> 72.69Improved
add inter-class separability loss L_sp to entropy minimization (ablation)BATCLIP (ViT-B/16) · CIFAR-100Cmean accuracy: 38.17 -> 41.84Improved
add inter-class separability loss L_sp to entropy minimization (ablation)BATCLIP (ViT-B/16) · ImageNet-Cmean accuracy: 24.03 -> 30.08Improved
add projection matching loss L_pm to entropy minimization (ablation)BATCLIP (ViT-B/16) · CIFAR-10Cmean accuracy: 60.65 -> 62.60Improved
add projection matching loss L_pm to entropy minimization (ablation)BATCLIP (ViT-B/16) · ImageNet-Cmean accuracy: 24.03 -> 25.21Improved
add projection matching loss L_pm to L_ent + L_sp (full objective) (ablation)BATCLIP (ViT-B/16) · CIFAR-10Cmean accuracy: 72.69 -> 73.85Improved
add projection matching loss L_pm to L_ent + L_sp (full objective) (ablation)BATCLIP (ViT-B/16) · ImageNet-Cmean accuracy: 30.08 -> 30.72Improved
add L_sp to L_ent + L_pm (full objective) (ablation)BATCLIP (ViT-B/16) · CIFAR-10Cmean accuracy: 62.60 -> 73.85Improved
use projection matching loss alone instead of entropy alone (ablation)BATCLIP (ViT-B/16) · CIFAR-100Cmean accuracy: 38.17 -> 36.63Hurt
scale L_pm and L_sp by 0.3 instead of 1.0 in the full objective (ablation)BATCLIP (ViT-B/16) · CIFAR-10Cmean accuracy: 73.31 vs 73.85No clear effect
use bimodal BATCLIP instead of SAR (vision-only TTA)BATCLIP vs SAR (ViT-B/16) · CIFAR-10Cmean accuracy: 67.37 -> 73.85Improved
use BATCLIP instead of WATT-S* with ViT-B/32BATCLIP vs WATT-S* (ViT-B/32) · CIFAR-10Cmean accuracy: 70.49 vs 68.26Hurt

Later papers that compared with this method

1 later accepted paper reports BATCLIP as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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