AI Paper Atlas

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

DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data

Junjie Wu, Jiangtao Xie, Zhaolin Zhang, Qilong Wang, Qinghua Hu, Peihua Li, Sen Xu

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Self-distillation for vision-language pretraining · 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
replace [cls] matching with feature distribution alignment (DALIP) on TOL-1MBioCLIP · 10 bio zero-shot tasksmean accuracy: 33.0 -> 36.8Improved
DALIP tuned on TOL-10MBioCLIP · 10 bio zero-shot tasksmean accuracy: 38.7 -> 46.3Improved
DALIP on TOL-10M vs ArborCLIP-O on 40M dataArborCLIP-O · 10 bio zero-shot tasksmean accuracy: 34.4 -> 46.3Improved
DALIP vs OpenCLIP tuned on PlantMix-1.3MOpenCLIP · General+plant zero-shotmean accuracy: 40.1 -> 50.0Improved
DALIP-SigLIP vs SigLIP/ProLIP on PlantMix-1.3MSigLIP · General+plant zero-shotmean accuracy: 57.7 -> 62.4Improved
DALIP vs OpenCLIP ViT-L on PlantMix-13MOpenCLIP ViT-L/14 · General+plant zero-shotmean accuracy: 57.1 -> 60.5Improved
DALIP vs FLAIR on PlantMix-13MFLAIR · General+plant zero-shotmean accuracy: 45.1 -> 56.4Improved
DALIP on PlantMix-13M vs original OpenCLIP in general domainOpenCLIP · General domain zero-shotaccuracy: 48.3 mean for original OpenCLIP vs 56.4 overallHurt
add 1st-order statistics to 2nd-order only (ablation)DALIP · PlantMix-1.3M plantplant mean accuracy: 44.8 -> 49.3Improved
add 2nd-order statistics to 1st-order only (ablation)DALIP · PlantMix-1.3M IN-1Kaccuracy: 30.7 -> 36.8Improved
use MBDC instead of BDC (ablation)DALIP · PlantMix-1.3M plantplant mean accuracy: 46.9 -> 49.3Improved
use MBDC instead of Moment Probing (ablation)DALIP · PlantMix-1.3M plantplant mean accuracy: 43.6 -> 49.3Improved

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