AI Paper Atlas

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

Universal Object Detection with Large Vision Model

Feng Lin, Wenze Hu, Yaowei Wang, Yonghong Tian, Guangming Lu, Fanglin Chen, Yong Xu, Xiaoyu Wang

IJCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 14 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 Cascade R-CNN heads instead of Faster R-CNN (ablation)frozen SEER-RegNet32gf detector · COCO valmAP: 29.0 -> 39.9Improved
add stacked NAS-FPN neck to Cascade R-CNN (ablation)Cascade R-CNN · COCO valmAP: 39.9 -> 45.7Improved
add Cascade RPN on top of stacked NAS-FPN (ablation)Cascade R-CNN + NAS-FPN · COCO valmAP: 45.7 -> 47.6Improved
stack more BiFPN blocks (ablation)Cascade R-CNN + BiFPN · COCO valmAP: 41.5 -> 41.1Hurt
freeze the SEER backbone instead of finetuning (ablation)Cascade R-CNN + NAS-FPN + Cascade RPN · COCO valmAP: 49.9 -> 51.4Improved
freeze the SEER-RegNet256gf backbone to cut memory (ablation)detector with SEER-RegNet256gf · MVDGPU memory (GB/image): 60 -> 15Improved
add HCLS to OID hierarchy loss (ablation)Cascade R-CNN (32gf) · COCO valmAP: 36.4 -> 37.1Improved
add HCLS to OID hierarchy loss (ablation)Cascade R-CNN (32gf) · OID valAP50: 64.8 -> 65.2Improved
add HCLS to OID hierarchy loss (ablation)Cascade R-CNN + NAS-FPN + Cascade RPN · OID valAP50: 67.6 -> 68.0Improved
use unified hierarchy loss instead of baseline (ablation)Cascade R-CNN + NAS-FPN + Cascade RPN · COCO valmAP: 44.1 -> 43.1Hurt
use naive loss suppression instead of baseline (ablation)Cascade R-CNN (32gf) · OID valAP50: 61.7 -> 62.7Improved
train universal detector on all three datasets instead of individually (ablation)Large-UniDet [S] · COCO valmAP: 47.6 -> 48.8Improved

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