AI Paper Atlas

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

Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis

Brian Kostadinov Shalon Isaac-Medina, Yona Falinie Abdul Gaus, Neelanjan Bhowmik, Toby P Breckon

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 7 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 OLN-SSOS/FFS (pseudo-class outlier synthesis on class-agnostic detector) instead of class-based VOS/SIREN/FFSobject-level anomaly detection · DBF6 OoD testOoD AR@100: 35.4 -> 48.8Improved
use OLN-SSOS/FFS instead of class-based baselinesobject-level anomaly detection · SIXRay10 OoD testOoD AR@100: 0.8 -> 35.6Improved
use OLN-FFS instead of best baseline SIRENobject-level anomaly detection · BDD100K / COCO OoDOoD AR@100: 10.5 -> 15.9Improved
use OLN-FFS instead of VOS without class labelsobject-level anomaly detection · PASCAL-VOC / COCO OoDOoD AR@100: 20.6 -> 17.8Hurt
replace class-supervised detector with class-agnostic OLN and pseudo-classesobject-level anomaly detection · LTDImaging in-distributionAR@100: 52.5 -> 17.8Hurt
add mask branch (OLN-Mask) to OLN-SSOS (ablation)OLN-SSOS · DBF6 OoD testOoD AR@100: 48.8 -> 58.9Improved
use FFS normalising-flow synthesis instead of Gaussian VOS synthesis (ablation)OLN-SSOS · DBF6 and LTDImaging OoDOoD AR@100: 58.9 -> 57.2 (DBF6 Mask); 18.2 -> 12.8 (LTD)Mixed
increase number of pseudo-labels (ablation)OLN-SSOS · DBF6, SIXRay10, VOC/COCOAR@10/AR@100Improved
increase number of pseudo-labels (ablation)OLN-SSOS · LTDImagingAR@10/AR@100Hurt
outlier sampling size 300 versus other sizes (50 to 10,000) (ablation)OLN-SSOS · VOC/COCOAR@10/AR@100Improved

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