AI Paper Atlas

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

VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching

Junyu Bi, Daixuan Cheng, Ping Yao, Bochen Pang, Yuefeng Zhan, Chuanguang Yang, Yujing Wang, Hao Sun, Weiwei Deng, Qi Zhang

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Self-distillation for vision-language pretraining · 4 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 MLM to the text encoder (ITC + ITM baseline) (ablation)VL-Match pretraining · NLVR2 + Flickr30kMeta-sum: 340.25 -> 340.47No clear effect
add generator-discriminator structure (ablation)VL-Match pretraining · NLVR2 + Flickr30kMeta-sum: 340.47 -> 342.41Improved
replace MLM with VL-RTD in the multimodal encoder (ablation)VL-Match pretraining · NLVR2 + Flickr30kMeta-sum: 342.41 -> 344.37Improved
add FG-ITM with NegGen negatives (ablation)VL-Match pretraining · NLVR2 + Flickr30kMeta-sum: 344.37 -> 346.59Improved
mask nouns and adjectives in NegGen instead of random tokens (ablation)NegGen · NLVR2 test-Paccuracy: 81.29 -> 82.23Improved
filter out generated texts that match the image in NegGen (ablation)NegGen · NLVR2 test-Paccuracy: 81.34 -> 82.23Improved
add FG-ITM (ablation)VL-Match · VALSE averageaccuracy: 69.34 -> 71.22Improved
add FG-ITM (ablation)VL-Match · SVO-Probes overallaccuracy: 87.96 -> 89.38Improved
set discriminator loss weight lambda to 10 instead of 1 (ablation)VL-RTD · NLVR2 + Flickr30kMeta-sum: 340.53 -> 344.37Improved
increase lambda beyond 10 (15, 20) (ablation)VL-RTD · NLVR2 + Flickr30kMeta-sum: 344.37 -> 342.74 (15), 343.63 (20)Hurt
replace MLM with VL-RTD (ablation)pretraining cost · pretraining FLOPsFLOPs (1e19): 1.898 -> 1.952Hurt

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