AI Paper Atlas

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

MAGVLT: Masked Generative Vision-and-Language Transformer

Sungwoong Kim, Daejin Jo, Donghoon Lee, Jongmin Kim

CVPR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 12 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 autoregressive decoding with masked iterative refinementVLT · MS-COCO validation, zero-shot T2IFID: 16.93 -> 12.08Improved
Replace autoregressive decoding with masked iterative refinementVLT · MS-COCO validation, zero-shot T2Ispeed: $1.00\times$ -> $8.12\times$Improved
Add joint image-and-text mask prediction (IT2IT) (ablation)MAGVLT · MS-COCO, I2TCIDEr: 53.5 -> 60.4Improved
Add joint image-and-text mask prediction (IT2IT) (ablation)MAGVLT · MS-COCO, T2IFID: 10.74 -> 12.08Hurt
Add UnrollMask (ablation)MAGVLT · MS-COCO, T2IFID: 14.12 -> 13.26Improved
Add UnrollMask (ablation)MAGVLT · MS-COCO, I2TCIDEr: 53.8 -> 56.5Improved
Add MixSel (ablation)MAGVLT · MS-COCO, I2TCIDEr: 56.5 -> 60.4Improved
Add MixSel (ablation)MAGVLT · MS-COCO, T2IFID: 12.08 -> 12.07No clear effect
Replace MixSel with MixRandom (mixed context without indicating the selected context) (ablation)MAGVLT · MS-COCO, I2TCIDEr: 60.4 -> 57.9Hurt
Replace MixSel with MixRandom (mixed context without indicating the selected context) (ablation)MAGVLT · MS-COCO, T2IFID: 12.08 -> 13.43Hurt
Increase the share of T2I training relative to I2T and IT2IT (ablation)MAGVLT · MS-COCO, T2IFID: 15.17 -> 12.08Improved
Increase the share of T2I training relative to I2T and IT2IT (ablation)MAGVLT · MS-COCO, I2TCIDEr: 61.7 -> 60.4Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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