mlsanityData to 14 Oct 2026

AnomalyHop: An SSL-based Image Anomaly Localization Method

arXiv 2105.03797 ↗First posted 8 May 2021cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work. AnomalyHop consists of three modules: 1) feature extraction via successive subspace learning (SSL), 2) normality feature distributions modeling via Gaussian models, and 3) anomaly map generation and fusion. Comparing with state-of-the-art image anomaly localization methods based on deep neural networks (DNNs), AnomalyHop is mathematically transparent, easy to train, and fast in its inference speed. Besides, its area under the ROC curve (ROC-AUC) performance on the MVTec AD dataset is 95.9%, which is among the best of several benchmarking methods. Our codes are publicly available at Github.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 8 May 2021.

Builds on

27 of 40 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Wide Residual Networkscited by 3,070
  3. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  4. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  5. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  6. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  7. 2020Explainable Deep One-Class Classificationcited by 127
  8. 2020DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentationcited by 54
  9. 2018Interpretable Convolutional Neural Networks via Feedforward Designcited by 49
  10. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
  11. 2019PointHop: An Explainable Machine Learning Method for Point Cloud Classificationcited by 46
  12. 2020PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classificationcited by 37
15 more
  1. 2016Understanding Convolutional Neural Networks with A Mathematical Modelcited by 33
  2. 2018Subspace Support Vector Data Descriptioncited by 31
  3. 2021DefakeHop: A Light-Weight High-Performance Deepfake Detectorcited by 31
  4. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  5. 2020PointHop++: A Lightweight Learning Model on Point Sets for 3D Classificationcited by 22
  6. 2021VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRIcited by 18
  7. 2020Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentationcited by 17
  8. 2020FaceHop: A Light-Weight Low-Resolution Face Gender Classification Methodcited by 16
  9. 2019Multimodal Subspace Support Vector Data Descriptioncited by 15
  10. 2020NITES: A Non-Parametric Interpretable Texture Synthesis Methodcited by 13
  11. 2021Successive Subspace Learning: An Overviewcited by 11
  12. 2020Low-Resolution Face Recognition In Resource-Constrained Environmentscited by 10
  13. 2019An Interpretable Compression and Classification System: Theory and Applicationscited by 6
  14. 2020Noise-Aware Texture-Preserving Low-Light Enhancementcited by 4
  15. 2021Dynamic Texture Synthesis by Incorporating Long-range Spatial and Temporal Correlationscited by 4

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 4; 2023: 3.

12 papers.

  1. 2021PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimationcited by 11
  2. 2021E-PixelHop: An Enhanced PixelHop Method for Object Classificationcited by 9
  3. 2021TGHop: An Explainable, Efficient and Lightweight Method for Texture Generationcited by 8
  4. 2021GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Cloudscited by 7
  5. 2022DefakeHop++: An Enhanced Lightweight Deepfake Detectorcited by 5
  6. 2022PAGER: Progressive Attribute-Guided Extendable Robust Image Generationcited by 5
  7. 2021Bridging Gap between Image Pixels and Semantics via Supervision: A Surveycited by 4
  8. 2022GENHOP: An Image Generation Method Based on Successive Subspace Learningcited by 4
  9. 2022Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarkingcited by 3
  10. 2023Enhancing Edge Intelligence with Highly Discriminant LNT Featurescited by 3
  11. 2023Green Steganalyzer: A Green Learning Approach to Image Steganalysiscited by 1
  12. 2023A Tiny Machine Learning Model for Point Cloud Object Classificationcited by 0