AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

VL-BERT: Pre-training of Generic Visual-Linguistic Representations

Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai

ICLR 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 774 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
pre-train VL-BERT on visual-linguistic and text-only data (ablation)VL-BERT_BASE · VCR Q→ARaccuracy: 54.2 -> 55.2Improved
pre-train VL-BERT on visual-linguistic and text-only data (ablation)VL-BERT_BASE · VQA v2.0 test-devaccuracy: 69.58 -> 71.16Improved
pre-train VL-BERT on visual-linguistic and text-only data (ablation)VL-BERT_BASE · RefCOCO+accuracy: 74.41 -> 79.88Improved
use masked language modeling with visual clues (ablation)VL-BERT pre-training · VCR Q→A val (0.5× fine-tuning epochs)accuracy: 72.9 -> 72.9No clear effect
add masked RoI classification with linguistic clues (ablation)VL-BERT pre-training · VQA test-dev (0.5× fine-tuning epochs)accuracy: 71.0 -> 71.1No clear effect
add masked RoI classification with linguistic clues (ablation)VL-BERT pre-training · RefCOCO+ detected regions val (0.5× fine-tuning epochs)accuracy: 69.1 -> 70.7Improved
add sentence-image relationship prediction (ablation)VL-BERT pre-training · VQA test-dev (0.5× fine-tuning epochs)accuracy: 71.1 -> 70.3Hurt
add sentence-image relationship prediction (ablation)VL-BERT pre-training · VCR Q→A val (0.5× fine-tuning epochs)accuracy: 73.0 -> 72.2Hurt
add text-only corpus during pre-training (ablation)VL-BERT pre-training · VCR QA→R val (0.5× fine-tuning epochs)accuracy: 73.1 -> 73.8Improved
add text-only corpus during pre-training (ablation)VL-BERT pre-training · VCR Q→A val (0.5× fine-tuning epochs)accuracy: 73.0 -> 73.4Improved
fine-tune Fast R-CNN visual feature parameters end-to-end (ablation)VL-BERT_BASE · VQA test-dev (0.5× fine-tuning epochs)accuracy: 71.1 -> 71.2Improved

Later papers that compared with this method

1 later accepted paper reports VL-BERT (Large) as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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