AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Qing Jiang, Feng Li, Zhaoyang Zeng, Shilong Liu, Tianhe Ren, Lei Zhang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 72 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 contrastive alignment between text and visual prompts (ablation)T-Rex2 Swin-T · LVIS val zero-shot, Visual-GAP: 30.2 -> 34.9Improved
add contrastive alignment between text and visual prompts (ablation)T-Rex2 Swin-T · LVIS val zero-shot, TextAP: 32.2 -> 34.8Improved
add contrastive alignment between text and visual prompts (ablation)T-Rex2 Swin-T · COCO val zero-shot, Visual-GAP: 38.7 -> 38.8No clear effect
joint text and visual training instead of visual-only training (ablation)T-Rex2 Swin-T · COCO val zero-shot, Visual-GAP: 14.0 -> 38.7Improved
naive joint training without alignment hurts text prompt (ablation)T-Rex2 Swin-T · COCO val zero-shot, TextAP: 46.4 -> 44.4Hurt
increase number of visual prompts from 1 to 16 (ablation)T-Rex2 Visual-G · COCO val zero-shotAP: 29.2 -> 38.8Improved
increase visual prompts from 16 to 64 (ablation)T-Rex2 Visual-G · LVIS val zero-shotAP: 34.9 -> 35.2No clear effect
add SA-1B self-training visual prompt data (ablation)T-Rex2-T Visual-I (Box) · COCO val zero-shotAP: 41.1 -> 56.6Improved
add SA-1B data to generic visual prompt training (ablation)T-Rex2-T Visual-G · COCO val zero-shotAP: 41.1 -> 38.8Hurt
add pseudo-labeled Bamboo classification data to text prompt training (ablation)T-Rex2-T Text · LVIS minival zero-shotAP: 34.9 -> 38.7Improved
text prompt versus visual prompt on common categoriesT-Rex2 Swin-T · COCO val-80 zero-shotAP: 45.8 vs 38.8Improved
visual prompt versus text prompt on long-tailed ODinWT-Rex2 Swin-T · ODinW 35val zero-shotAP avg: 18.0 -> 23.6Improved

Later papers that compared with this method

6 later accepted papers report T-Rex2 as a baseline in their results tables; 5 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