AI Paper Atlas

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

UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling

Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Faisal Ahmed, Zicheng Liu, Yumao Lu, Lijuan Wang

ECCV 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 110 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 pre-training (ablation)UniTAB (task-specific finetuning) · Refcocog val-uAcc@0.5: 63.56 -> 79.96Improved
add pre-training (ablation)UniTAB (multi-task finetuning) · Flickr30k grounded captioningCIDEr: 61.1 -> 63.4Improved
replace task-specific finetuning by multi-task finetuning (Shared) after pre-training (ablation)UniTAB · Refcocog val-uAcc@0.5: 79.96 -> 84.46Improved
replace task-specific finetuning by multi-task finetuning (Shared) after pre-training (ablation)UniTAB · Flickr30k grounded captioningCIDEr: 65.6 -> 63.4Hurt
add task-specific finetuning after multi-task finetuning (Pre-finetuning) (ablation)UniTAB Shared · Flickr30k grounded captioningCIDEr: 63.4 -> 69.7Improved
add 4M image-text pairs without boxes to pre-training (ablation)UniTAB Separate · Flickr30k grounded captioningCIDEr: +8.6 CIDEr (65.6 -> 74.2)Improved
add 4M image-text pairs without boxes to pre-training (ablation)UniTAB Separate · COCO captioningCIDEr: +3.8 CIDEr (119.3 -> 123.1)Improved
add 4M image-text pairs without boxes to pre-training (ablation)UniTAB Separate · VQAv2 Karpathy testaccuracy: +2.5% absolute (66.6 -> 69.1)Improved
add extra detection box annotations to pre-training (ablation)UniTAB Separate · Refcocog val-uAcc@0.5: 79.96 -> 83.78Improved
add extra detection box annotations to pre-training (ablation)UniTAB Separate · Flickr30k grounded captioningCIDEr: 65.6 -> 70.0Improved
add obj tokens around word-box segments (ablation)UniTAB Separate · Refcocog val-uAcc@0.5: 79.31 -> 80.23Improved
add decoder type embedding (ablation)UniTAB Separate · Refcocog val-uAcc@0.5: 80.23 -> 80.54No clear effect

Later papers that compared with this method

1 later accepted paper reports UniTAB 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