AI Paper Atlas

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

T-Rex2++: Toward Generic Object Perception via Text-Visual Prompt Synergy

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

TPAMI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 2 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 text prompt · LVIS-Val zero-shotAP: 32.2 -> 34.8 (+2.6)Improved
add contrastive alignment between text and visual prompts (ablation)T-Rex2 visual-G prompt · LVIS-Val zero-shotAP: 30.2 -> 34.9 (+4.7)Improved
add contrastive alignment between text and visual prompts (ablation)T-Rex2 text prompt · COCO-Val zero-shotAP: 44.4 -> 45.8 (+1.4)Improved
add contrastive alignment between text and visual prompts (ablation)T-Rex2 visual-G prompt · COCO-Val zero-shotAP: 38.7 -> 38.8 (+0.1)No clear effect
train text and visual prompts jointly without alignment instead of visual only (ablation)T-Rex2 visual-G prompt · COCO-Val zero-shotAP: 14.0 -> 38.7Improved
naive joint training of both prompts instead of text only (ablation)T-Rex2 text prompt · COCO-Val zero-shotAP: 46.4 -> 44.4Hurt
increase number of visual prompts per category from 1 to 16 (ablation)T-Rex2 visual-G prompt · COCO-Val zero-shotAP: 29.2 -> 38.8Improved
increase number of visual prompts per category from 16 to 64 (ablation)T-Rex2 visual-G prompt · COCO-Val zero-shotAP: 38.8 -> 41.4Improved
combine text and visual-G prompts at inference (ablation)T-Rex2 · LVIS-Val zero-shotAP: 34.8 -> 37.0Improved
combine text and visual-G prompts at inference (ablation)T-Rex2 · COCO-Val zero-shotAP: 45.8 -> 42.5Hurt
add Bamboo dataset to text prompt training (ablation)T-Rex2-T text prompt · LVIS-Minival zero-shotAP: 34.9 -> 38.7 (+3.8AP)Improved
add Bamboo dataset to text prompt training (ablation)T-Rex2-T text prompt · COCO-Val zero-shotAP: 46.1 -> 45.7 (-0.4AP)Hurt

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