AI Paper Atlas

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

Toward Unsupervised, Multi-Object Discovery in Large-Scale Image Collections

Huy V. Vo, Patrick Pérez, Jean Ponce

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 59 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 one-region-per-group regularization (rOSD) to OSD (ablation)OSD with our proposals · VOC_all colocalization (VGG16)CorLoc: 44.7 -> 45.8Improved
add one-region-per-group regularization (rOSD) to OSD (ablation)OSD with our proposals · VOC_all single-object discovery (VGG16)CorLoc: 48.7 -> 49.2Improved
add one-region-per-group regularization (rOSD) to OSD (ablation)OSD with our proposals · OD and VOC_6x2 colocalization (VGG16)CorLoc: 89.0 -> 89.0; 73.6 -> 73.3No clear effect
add one-region-per-group regularization (rOSD) to OSD (ablation)OSD with our proposals · VOC_all multi-object discovery (VGG19)detection rate: 34.8 -> 37.6Improved
add one-region-per-group regularization (rOSD) to OSD (ablation)OSD with our proposals · VOC12 multi-object discovery (VGG19)detection rate: 36.8 -> 40.4Improved
use our unsupervised CNN proposals instead of randomized Prim (ablation)OSD · VOC_all colocalization (VGG16)CorLoc: 42.8 -> 44.7Improved
use our unsupervised CNN proposals instead of selective search (ablation)OSD · VOC_all colocalization (VGG16)CorLoc: 30.9 -> 44.7Improved
add two-stage large-scale strategy (ablation)rOSD · VOC_all single-object discoveryCorLoc: 42.8 -> 49.4Improved
add two-stage large-scale strategy (ablation)rOSD · COCO_20k single-object discoveryCorLoc: 44.5 -> 48.5Improved
add two-stage large-scale strategy (ablation)rOSD · COCO_20k multi-object discoverydetection rate: 11.6 -> 12.0Improved
add ensemble method of Vo et al. (ablation)OSD with our proposals · VOC_6x2 colocalization (VGG16)CorLoc: 73.6 -> 75.3Mixed
use standout score instead of confidence score (ablation)OSD with our proposals · OD vs VOC_6x2 colocalizationCorLoc: 83.7 -> 89.0; 73.6 -> 64.1Mixed

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