AI Paper Atlas

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

UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks

Jiasen Lu, Christopher Clark, Rowan Zellers, Roozbeh Mottaghi, Aniruddha Kembhavi

ICLR 2023 · 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
scale model from SMALL to XL (71M to 2.9B params)Unified-IO · GRIT testaverage accuracy: 45.4 to 64.3Improved
remove image synthesis task group during multi-task training (ablation)Unified-IO LARGE · GRIT keypoint (ablation split)keypoint accuracy: 69.2 to 18.3Hurt
remove captioning task group (ablation)Unified-IO LARGE · GRIT VQA and localizationaccuracy: VQA 65.7 to 68.0 (improves when removed)No clear effect
remove NLP task group during multi-task training (ablation)Unified-IO LARGE · GRIT categorizationcategorization accuracy: 50.3 to 56.1 when removed (removing helps)Hurt
remove task groups generally (dense, sparse, classification, V&L, language modelling) (ablation)Unified-IO LARGE · GRIT and MNLItask accuracyNo clear effect
use pre-trained VQ-GAN image tokenizer without surface normal dataUnified-IO XL · GRIT surface normalaccuracy: 44.3 vs NLL-AngMF 49.6Hurt
2-stage keypoint inference (locate person, then keypoints)Unified-IO XL · GRIT keypointkeypoint accuracy: 68.1 vs Mask R-CNN 70.8Hurt
use prompt paraphrases for referring expressions instead of training prompt (ablation)Unified-IO · GRIT referring expression ablationRefexp score: 78.9 to as low as 0.1Hurt

Later papers that compared with this method

4 later accepted papers report UnifiedIO-XL 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