AI Paper Atlas

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

DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection

Gautam Rajendrakumar Gare, Neehar Peri, Matvei Popov, Shruti Jain, John Galeotti, Deva Ramanan

ECCV 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 few-shot images as in-context examples to class names and instructions (ablation)Qwen3-VL (8B) · RF20-VL (20 datasets, 10-shot)mAP: 11.4 -> 7.0Hurt
add few-shot images as in-context examples (ablation)Qwen2.5-VL (7B) · RF20-VL (20 datasets, 10-shot)mAP: 6.2 -> 1.8Hurt
add few-shot images as in-context examples (ablation)Gemini 3 Pro · RF20-VL (20 datasets, 10-shot)mAP: 23.0 -> 23.9Improved
add class instructions to class names (ablation)Qwen3-VL (30B-A3B) · RF20-VL (20 datasets, 10-shot)mAP: 10.7 -> 11.9Improved
apply DetPO prompt optimizationQwen3-VL (30B-A3B) · RF20-VL (20 datasets, 10-shot)mAP: 11.9 -> 19.4Improved
add VQA Score confidence re-scoring (ablation)Qwen3-VL (30B-A3B) + DetPO · RF20-VL (20 datasets, 10-shot)mAP: 19.4 -> 21.6Improved
replace self-reported confidence with SigLIPv2 score (ablation)Qwen3-VL (30B-A3B) + DetPO · RF20-VL (20 datasets, 10-shot)mAP: 19.4 -> 16.4Hurt
use DetPO instead of GEPAGemini 3 Pro · RF20-VL (20 datasets, 10-shot)mAP: 25.6 -> 26.4Improved
use MIPROv2 prompt optimizationQwen3-VL (30B-A3B) · RF20-VL (20 datasets, 10-shot)mAP: 11.9 -> 10.7Hurt
apply DetPO prompt optimizationQwen2.5-VL (7B) · RF20-VL (20 datasets, 10-shot)mAP: 6.2 -> 9.1Improved
apply DetPO prompt optimizationQwen2.5-VL (72B) · RF20-VL (20 datasets, 10-shot)mAP: 10.4 -> 15.7Improved
add VQA Score re-scoring (ablation)Qwen3-VL (8B) + DetPO · RF20-VL (20 datasets, 10-shot)mAP: 15.3 -> 17.5Improved

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