AI Paper Atlas

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

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

Alexander Kolesnikov, André Susano Pinto, Lucas Beyer, Xiaohua Zhai, Jeremiah J. Harmsen, Neil Houlsby

NeurIPS 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Human-like visual cognition in VLMs · 23 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
initialize LM encoder with pre-trained weights (ablation)UViM · COCO Panoptic holdoutPQ: 41.4 -> 43.7Improved
scale LM from Base to Large with pre-training (ablation)UViM · COCO Panoptic holdoutPQ: 41.9 -> 43.7Improved
scale LM from Base to Large when training from scratch (ablation)UViM · COCO Panoptic holdoutPQ: 41.0 -> 41.4No clear effect
add code dropout in stage I (ablation)UViM · COCO Panoptic holdoutPQ (final model): 42.2 -> 43.7Improved
add code dropout in stage I (ablation)UViM · NYU Depth v2RMSENo clear effect
add restricted oracle guiding code (ablation)base model · COCO Panoptic holdoutPQ: 25.5 -> 75.7Improved
make LM autoregressive instead of single-pass (ablation)UViM LM · COCO Panoptic holdoutPQ: 33.3 -> 43.7Improved
make LM autoregressive instead of single-pass (ablation)UViM LM · NYU Depth v2RMSE: 0.55 -> 0.47Improved
feed image input to base model in stage I (ablation)UViM · COCO Panoptic holdoutPQ: 39.1 -> 43.7Improved
feed image input to base model in stage I (ablation)UViM · NYU Depth v2RMSE: within 0.005 RMSENo clear effect
vary guiding code length and dictionary size (ablation)UViM · COCO Panoptic holdoutPQMixed

Later papers that compared with this method

2 later accepted papers report UViM as a baseline in their results tables; 2 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