AI Paper Atlas

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

YOLOE: Real-Time Seeing Anything

Ao Wang, Lihao Liu, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 185 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 RepRTA auxiliary text-embedding network (re-parameterized at inference) (ablation)YOLOE-v8-L · LVIS minival zero-shotAP: 31.5 -> 33.5Improved
remove cross-modality fusion for speed (ablation)YOLO-Worldv2-L · LVIS minival zero-shotAP: 31.9 -> 30.0Hurt
add global negative dictionary instead of empty-string negatives (ablation)YOLO-Worldv2-L (30 epochs) · LVIS minival zero-shotAP: 31.0 -> 31.9Improved
use MobileCLIP-B(LT) text encoder (ablation)YOLOE without cross-modal fusion · LVIS minival zero-shotAP: 30.0 -> 31.5Improved
reduce training epochs from 100 to 30 (ablation)YOLO-Worldv2-L · LVIS minival zero-shotAP: 33.0 -> 31.0Hurt
add segmentation head and train detection and segmentation jointly (ablation)YOLOE-v8-L · LVIS minival zero-shotAP: 33.5 -> 33.3Hurt
replace mask pooling with SAVPE activation branch for visual prompts (ablation)YOLOE visual prompt · LVIS minival zero-shot (visual prompt)AP: +1.5 APImproved
increase SAVPE group number A from 1 to 16 (ablation)SAVPE · LVIS minival zero-shot (visual prompt)AP: 31.9 AP at A=16No clear effect
use LRPC lazy retrieval instead of matching full vocabulary against all anchor points (ablation)YOLOE prompt-free · LVIS minival prompt-freeinference speedup: 1.7x / 1.3x speedup for YOLOE-v8-S / L, same APImproved
raise LRPC filtering threshold delta for more speed (ablation)YOLOE-v8-S LRPC · LVIS minival prompt-freeAP: 1.9x speedup with 0.2 AP dropMixed
fine-tune YOLOE fully on COCO with far fewer epochs instead of training YOLOv8-L from scratchYOLOE-v8-L · COCO valAP^b: 52.4 -> 53.0Improved
joint detection and segmentation training in YOLOE vs YOLO-Worldv2 on frequent categoriesYOLOE-v8-M/L · LVIS minival zero-shotAP_f: YOLOE-v8-L 37.3 vs YOLO-Worldv2-L 38.1Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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