AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

AnnofreeOD: Detecting All Classes at Low Frame Rates Without Human Annotations

Boyi Sun, Yuhang Liu, Houxin He, Yonglin Tian, Fei-Yue Wang

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D 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
use 2D-to-3D distillation without scene flow instead of UNIONAnnofreeOD · nuScenes val (3-class)mAP: 25.1 -> 34.4Improved
use 2D-to-3D distillation without scene flow instead of UNIONAnnofreeOD · nuScenes val (3-class)NDS: 24.4 -> 36.6Improved
use AnnofreeOD instead of UNION for class-agnostic detectionAnnofreeOD · nuScenes val (class-agnostic)AP: 39.5 -> 45.5Improved
use AnnofreeOD instead of UNION for class-agnostic detectionAnnofreeOD · nuScenes val (class-agnostic)NDS: 31.7 -> 35.8Improved
use AnnofreeOD instead of UNION for class-agnostic detectionAnnofreeOD · nuScenes val (class-agnostic)AOE: 0.876 -> 1.441Hurt
use AnnofreeOD instead of UNION for class-agnostic detectionAnnofreeOD · nuScenes val (class-agnostic)AVE: 0.837 -> 1.956Hurt
use AnnofreeOD instead of UNION for class-agnostic detectionAnnofreeOD · nuScenes val (class-agnostic)ATE: 0.590 -> 0.328Improved
compare annotation-free AnnofreeOD with supervised 10-class detectorAnnofreeOD · nuScenes val (10-class)mAP: 60.0 -> 22.2Mixed
compare AnnofreeOD with 1% labeled supervised training (3-class)AnnofreeOD · nuScenes val (3-class)mAP: 24.3 -> 34.4Improved
compare AnnofreeOD with 10% labeled supervised training (class-agnostic)AnnofreeOD · nuScenes val (class-agnostic)AP: 61.2 -> 45.5Hurt
compare AnnofreeOD with 10% labeled supervised training (3-class)AnnofreeOD · nuScenes val (3-class)mAP: 45.9 -> 34.4Hurt
use AnnofreeOD instead of UNION for Cyclist APAnnofreeOD · nuScenes val (3-class)Cyclist AP: 0.0 -> 7.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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