AI Paper Atlas

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

UNITER: UNiversal Image-TExt Representation Learning

Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 2,280 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/ITM/MRM pre-training tasks jointly instead of no pre-training (ablation)UNITER-base · Meta-Sum of VQA, NLVR2, Flickr30K, RefCOCO+Meta-Sum: 314.34 -> 400.93Improved
add ITM pre-training only (ablation)UNITER-base · Meta-SumMeta-Sum: 346.24 -> 385.29Improved
add MRFR alone on top of text-only MLM init (ablation)UNITER-base · Meta-SumMeta-Sum: 346.24 -> 344.66No clear effect
add ITM to MLM (ablation)UNITER-base · Meta-SumMeta-Sum: 386.10 -> 393.04Improved
use MRC-kl rather than MRC as masked region modeling variant (ablation)UNITER-base · Meta-SumMeta-Sum: 393.97 -> 397.09Improved
combine MRC-kl and MRFR (ablation)UNITER-base · Meta-SumMeta-Sum: 397.09 -> 399.97Improved
add word-region alignment (WRA) pre-training (ablation)UNITER-base · Meta-SumMeta-Sum: 399.97 -> 400.93Improved
use conditional masking instead of joint random masking (ablation)UNITER-base · Meta-SumMeta-Sum: 396.51 -> 399.97Improved
pre-train on out-of-domain data only instead of in-domain (ablation)UNITER-base · Meta-SumMeta-Sum: 400.93 -> 396.91Hurt
add out-of-domain data to in-domain pre-training data (ablation)UNITER-base · Meta-SumMeta-Sum: 400.93 -> 405.24Improved
add WRA pre-training to UNITER-large (ablation)UNITER-large · Flickr30K zero-shot text retrievalR@1: 77.50 -> 83.60Improved
add second-stage pre-training on VCR data (ablation)UNITER-large · VCRQ->AR accuracy: 53.52 -> 55.6Improved

Later papers that compared with this method

5 later accepted papers report UNITER Base as a baseline in their results tables; 3 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