</> Code with Papers by Syntology

Papers › Unlocking the Potential of Reverse Distillation for Anomaly Detection

Unlocking the Potential of Reverse Distillation for Anomaly Detection

10 Dec 2024arXiv:2412.07579archive 2025-07-28

Xinyue Liu, Jianyuan Wang, Biao Leng, Shuo Zhang

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To addresses this problem, the widely accepted Reverse Distillation (RD) paradigm designs the asymmetry teacher and student, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student's ability to generate normal features and optimizes the teacher's differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD's potential.

PaperPDFCode

Code

hito2448/urd officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionDecoderKnowledge DistillationUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection BTAD URD Detection AUROC 93.9 #11 of 15 Archive leaderboard report
Anomaly Detection BTAD URD Segmentation AP 65.2 #11 of 15 Archive leaderboard report
Anomaly Detection BTAD URD Segmentation AUPRO 78.5 #11 of 15 Archive leaderboard report
Anomaly Detection BTAD URD Segmentation AUROC 98.1 #11 of 15 Archive leaderboard report
Anomaly Detection MVTec AD URD Detection AUROC 99.2 #41 of 148 Archive leaderboard report
Anomaly Detection MVTec AD URD Segmentation AP 72.4 #41 of 148 Archive leaderboard report
Anomaly Detection MVTec AD URD Segmentation AUPRO 96.3 #41 of 148 Archive leaderboard report
Anomaly Detection MVTec AD URD Segmentation AUROC 99.0 #41 of 148 Archive leaderboard report
Anomaly Detection VisA URD Detection AUROC 96.5 #19 of 50 Archive leaderboard report
Anomaly Detection VisA URD Segmentation AUPRO (until 30% FPR) 95.1 #19 of 50 Archive leaderboard report
Anomaly Detection VisA URD Segmentation AUROC 99.1 #19 of 50 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections