AI Paper Atlas

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

NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection

Yupeng Zhang, Ruize Han, Zhiwei Chen, Wei Feng, Liang Wan

CVPR 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 NoOVD (latent novel discovery + self-distillation + R-RPN)CLIPSelf + F-ViT ViT-B/16 · OV-LVISAPr: 25.4 -> 28.3Improved
add NoOVDDeCLIP + F-ViT ViT-L/14 · OV-LVISAPr: 36.9 -> 39.2Improved
add NoOVDCLIPSelf + F-ViT ViT-B/16 · OV-COCOAP50 novel: 35.8 -> 37.9Improved
add NoOVDCLIPSelf + F-ViT ViT-L/14 · OV-COCOAP50 base: 64.8 -> 64.7No clear effect
add NoOVDDeCLIP + F-ViT ViT-L/14 · Objects365 (cross-dataset)APr: 22.3 -> 23.3Improved
add K-FPN features instead of CLIP-top (ablation)NoOVD ViT-B/16 · OV-LVISAPr: 26.4 -> 27.5Improved
add R-RPN at test time (ablation)F-ViT baseline ViT-B/16 · OV-LVISAPr: 25.4 -> 26.7Improved
use CLIP top-layer feature for discovery (ablation)F-ViT baseline ViT-B/16 · OV-LVISAPr: 25.4 -> 26.4Improved
tune K-FPN fusion weight W from 0.8 to 0.3 (ablation)K-FPN · OV-LVIS (CLIPSelf ViT-B/16)AP: 19.1 -> 26.7Improved
set R-RPN alpha 0.5 vs 0.9 (ablation)R-RPN · OV-LVIS (CLIPSelf ViT-B/16)AP: 25.5 -> 26.7Improved
use L2 instead of cosine loss for distillation (ablation)NoOVD · OV-LVIS (CLIPSelf ViT-B/16)APr: 17.3 -> 28.3Improved
use L2 instead of L1/SmoothL1 (ablation)NoOVD · OV-LVIS (CLIPSelf ViT-B/16)APr: 27.8/28.0 -> 28.3No clear effect

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