AI Paper Atlas

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

DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts

Bo Qian, Dahu Shi, Xing Wei

ICLR 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 image-text contrastive alignment (ablation)VIS-GDINO-T · COCO / LVIS-minivalAP: 21.1 -> 29.2; 17.2 -> 23.4Improved
add global prompt integration (ablation)VIS-GDINO-T + alignment · COCO / LVIS-minivalAP: 29.2 -> 35.6; 23.4 -> 33.0Improved
add visual-textual prompt relation distillation (ablation)DETR-ViP-T intermediate · COCO / LVIS-minivalAP: 35.6 -> 41.5; 33.0 -> 39.5Improved
add naive encoder fusion from Grounding DINO (ablation)DETR-ViP-T intermediate · COCO / LVIS-minivalAP: 41.5 -> 41.3; 39.5 -> 39.1Hurt
use encoder selective fusion instead of naive encoder fusion (ablation)DETR-ViP-T intermediate · COCO / LVIS-minivalAP: 41.3 -> 42.2; 39.1 -> 40.6Improved
add naive decoder fusion (ablation)DETR-ViP-T intermediate · COCO / LVIS-minivalAP: 42.2 -> 40.8; 40.6 -> 25.5Hurt
add decoder selective fusion (ablation)DETR-ViP-T intermediate · COCO / LVIS-minivalAP: 42.2 -> 43.2; 40.6 -> 41.1Improved
replace supervised contrastive loss with relation distillation loss (ablation)DETR-ViP-T · COCO / LVIS-minivalAP: 42.6 -> 43.2; 40.4 -> 41.1Improved
raise distillation weight lambda from 1.0 to 10.0 (ablation)DETR-ViP-T · LVISAP: 40.5 -> 41.1Improved
raise distillation weight lambda from 10.0 to 20.0 (ablation)DETR-ViP-T · LVISAP: 41.1 -> 39.8Hurt
vary selective fusion threshold theta from 0.1 to 0.5 (ablation)DETR-ViP-T · LVISAP: 41.1 -> 39.2Hurt
lower selective fusion threshold theta from 0.1 to 0.05 (ablation)DETR-ViP-T · LVISAP: 41.1 -> 38.7Hurt

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