AI Paper Atlas

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

Generalizable Object Re-Identification via Visual In-Context Prompting

Zhizhong Huang, Xiaoming Liu

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 4 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 ICL-generated visual prompts to triplet fine-tuned DINOv2 (ablation)Triplet · ShopID10K (novel categories)mAP: 50.3 -> 56.3Improved
add patch alignment loss (ablation)VICP · ShopID10K (novel categories)mAP: 56.3 -> 58.5Improved
add patch alignment loss (ablation)VICP · PetFace (novel categories)mAP: 50.8 -> 51.2Improved
use LLM in-context output directly instead of visual prompts (ablation)VICP · ShopID10K (novel categories)mAP: 56.3 -> 39.6Hurt
use 32 in-context examples instead of 64 (ablation)VICP · ShopID10K (novel categories)mAP: 58.5 -> 55.7Hurt
use 128 in-context examples instead of 64 (ablation)VICP · ShopID10K (novel categories)mAP: 58.5 -> 56.8Hurt
use 16 latent tokens instead of 32 (ablation)VICP · ShopID10K (novel categories)mAP: 58.5 -> 55.9Hurt
use 64 latent tokens instead of 32 (ablation)VICP · ShopID10K (novel categories)mAP: 58.5 -> 57.1Hurt
fine-tune DINOv2 with triplet loss on base categoriesDINOv2 · ShopID10K (novel categories)mAP: 34.1 -> 50.3Improved
use triplet loss instead of ArcFaceDINOv2 fine-tuning · ShopID10K (novel categories)mAP: 45.3 -> 50.3Improved
add few-shot fine-tuning (Triplet+)Triplet · ShopID10K (novel categories)mAP: 50.3 -> 54.8Improved
replace Triplet+ with VICP promptsTriplet+ · ShopID10K (novel categories)mAP: 54.8 -> 58.5Improved

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