mlsanityData to 14 Oct 2026

PaSTe: Improving the Efficiency of Visual Anomaly Detection at the Edge

arXiv 2410.11591 ↗First posted 15 Oct 2024cs.CV cs.AI cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Visual Anomaly Detection (VAD) has gained significant research attention for its ability to identify anomalous images and pinpoint the specific areas responsible for the anomaly. A key advantage of VAD is its unsupervised nature, which eliminates the need for costly and time-consuming labeled data collection. However, despite its potential for real-world applications, the literature has given limited focus to resource-efficient VAD, particularly for deployment on edge devices. This work addresses this gap by leveraging lightweight neural networks to reduce memory and computation requirements, enabling VAD deployment on resource-constrained edge devices. We benchmark the major VAD algorithms within this framework and demonstrate the feasibility of edge-based VAD using the well-known MVTec dataset. Furthermore, we introduce a novel algorithm, Partially Shared Teacher-student (PaSTe), designed to address the high resource demands of the existing Student Teacher Feature Pyramid Matching (STFPM) approach. Our results show that PaSTe decreases the inference time by 25%, while reducing the training time by 33% and peak RAM usage during training by 76%. These improvements make the VAD process significantly more efficient, laying a solid foundation for real-world deployment on edge devices.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

26 of 40 references.

References · 26

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2016Wide Residual Networkscited by 3,070
  3. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  5. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  6. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  7. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  9. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  10. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  11. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  12. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
14 more
  1. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  2. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  3. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  4. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  5. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 146
  6. 2023Neural Architecture Search: Insights from 1000 Paperscited by 139
  7. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  8. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
  9. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  10. 2021MicroNet: Improving Image Recognition with Extremely Low FLOPscited by 26
  11. 2019MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devicescited by 18
  12. 2021PhiNets: a scalable backbone for low-power AI at the edgecited by 16
  13. 2024Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learningcited by 13
  14. 2023tinyCLAP: Distilling Constrastive Language-Audio Pretrained Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 8.

16 papers.

Sort:

  1. 2025Memory Efficient Continual Learning for Edge-Based Visual Anomaly Detectioncited by 4
  2. 2025Towards Continual Visual Anomaly Detection in the Medical Domaincited by 3
  3. 2026TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detectioncited by 2
  4. 2026Efficient Visual Anomaly Detection at the Edge: Enabling Real-Time Industrial Inspection on Resource-Constrained Devicescited by 2
  5. 2025From Vision to Sound: Advancing Audio Anomaly Detection with Vision-Based Algorithmscited by 1
  6. 2025Towards Scalable IoT Deployment for Visual Anomaly Detection via Efficient Compressioncited by 1
  7. 2026Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutionscited by 1
  8. 2025Evaluating Modern Visual Anomaly Detection Approaches in Semiconductor Manufacturing: A Comparative Studycited by 0
  9. 2025MoViAD: A Modular Library for Visual Anomaly Detectioncited by 0
  10. 2025Explainable Visual Anomaly Detection via Concept Bottleneck Modelscited by 0
  11. 2025On-Device Continual Learning for Unsupervised Visual Anomaly Detection in Dynamic Manufacturingcited by 0
  12. 2026VAD4Space: Visual Anomaly Detection for Planetary Surface Imagerycited by 0
4 more
  1. 2026AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Drivingcited by 0
  2. 2026Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditionscited by 0
  3. 2026Value-order Decomposition for Generalist Anomaly Detectioncited by 0
  4. 2026LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge
  2. 2026AdapTS: Lightweight Teacher-Student Approach for Multi-Class and Continual Visual Anomaly Detection
  3. 2024Video Anomaly Detection in 10 Years: A Survey and Outlook
  4. 2025VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion
  5. 2025The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
  6. 2026AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation
  7. 2026Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection
  8. 2025ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categories