mlsanityData to 7 Oct 2026

[Reproducibility Report] Explainable Deep One-Class Classification

arXiv 2206.02598 ↗First posted 6 Jun 2022cs.CV cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Fully Convolutional Data Description (FCDD), an explainable version of the Hypersphere Classifier (HSC), directly addresses image anomaly detection (AD) and pixel-wise AD without any post-hoc explainer methods. The authors claim that FCDD achieves results comparable with the state-of-the-art in sample-wise AD on Fashion-MNIST and CIFAR-10 and exceeds the state-of-the-art on the pixel-wise task on MVTec-AD. We reproduced the main results of the paper using the author's code with minor changes and provide runtime requirements to achieve if (CPU memory, GPU memory, and training time). We propose another analysis methodology using a critical difference diagram, and further investigate the test performance of the model during the training phase.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 34 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

16 of 34 references.

References · 16

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  4. 2018Deep learning for time series classification: a reviewcited by 575
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  7. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  8. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
  9. 2020Explainable Deep One-Class Classificationcited by 126
  10. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  11. 2020Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Imagescited by 52
  12. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
4 more
  1. 2020Rethinking Assumptions in Deep Anomaly Detectioncited by 45
  2. 2021Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localizationcited by 32
  3. 2021Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentationcited by 26
  4. 2015Analyzing Classifiers: Fisher Vectors and Deep Neural Networkscited by 24

Built on by

Not cited yet.