mlsanityData to 14 Oct 2026

LBL: Logarithmic Barrier Loss Function for One-class Classification

arXiv 2307.10753 ↗First posted 20 Jul 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

One-class classification (OCC) aims to train a classifier only with the target class data and attracts great attention for its strong applicability in real-world application. Despite a lot of advances have been made in OCC, it still lacks the effective OCC loss functions for deep learning. In this paper, a novel logarithmic barrier function based OCC loss (LBL) that assigns large gradients to the margin samples and thus derives more compact hypersphere, is first proposed by approximating the OCC objective smoothly. But the optimization of LBL may be instability especially when samples lie on the boundary leading to the infinity loss. To address this issue, then, a unilateral relaxation Sigmoid function is introduced into LBL and a novel OCC loss named LBLSig is proposed. The LBLSig can be seen as the fusion of the mean square error (MSE) and the cross entropy (CE) and the optimization of LBLSig is smoother owing to the unilateral relaxation Sigmoid function. The effectiveness of the proposed LBL and LBLSig is experimentally demonstrated in comparisons with several popular OCC algorithms on different network structures. The source code can be found at https://github.com/ML-HDU/LBL_LBLSig.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 48 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

19 of 48 references.

References · 19

  1. 2021Convex optimizationcited by 2,515
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  4. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  5. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  6. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  7. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  8. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  9. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  10. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  11. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  12. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
7 more
  1. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  2. 2015Learning Deep Representations of Appearance and Motion for Anomalous Event Detectioncited by 75
  3. 2019GODS: Generalized One-class Discriminative Subspaces for Anomaly Detectioncited by 64
  4. 2017Improving Pairwise Ranking for Multi-label Image Classificationcited by 40
  5. 2020MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detectioncited by 31
  6. 2021Transformaly -- Two (Feature Spaces) Are Better Than Onecited by 25
  7. 2019adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detectioncited by 11

Built on by

Not cited yet.