AI Paper Atlas

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

Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes

Zelong Zeng, Kaname Tomite

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly 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 RWPM random-walk embedding refinement at inferencePEBAL · Fishyscapes Lost&FoundAP: 58.81 -> 66.85Improved
add RWPMBalanced Energy · Road AnomalyFPR95: 41.46 -> 32.10Improved
add RWPMMask2Anomaly · Fishyscapes Lost&FoundAP: 65.27 -> 65.38No clear effect
add RWPMRbA · SMIYC Anomaly Track component-levelmean F1: 46.80 -> 58.44Improved
partition embedding map into n x n sub-maps instead of full map (ablation)RWPM · Road AnomalyFPS: 0.32 -> 2.04 FPS, AP 87.90 -> 87.34Improved
add sub-map calibration when n>2 (ablation)RWPM · Road AnomalyFPR95: 6.31 -> 5.32 (n=4)Improved
add calibration at n=2 (ablation)RWPM · Road AnomalyAP: 87.34 -> 87.18No clear effect
use limited iterations instead of closed form (T=20 vs infinity) (ablation)RWPM · Road AnomalyAP: 87.51 -> 87.34, FPS 0.29 -> 2.04No clear effect
increase iteration number T (ablation)RWPM · Road AnomalyAP: 86.89 (T=5) -> 87.54 (T=100), FPS 3.70 -> 0.50Mixed
reduce embeddings by resizing or superpixels instead of partitioning (ablation)RWPM · Road AnomalyAP: memory 23.82GiB (resize 0.9) vs 7.24GiBHurt
add RWPM to RbA for in-distribution segmentationRbA · Cityscapes valmIoU: 81.93 -> 82.16Improved

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