REVIEW 5 cited by
Learning and Evaluating Representations for Deep One-class Classification
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn better representations, but also permits building one-class classifiers that are faithful to the target task. We argue that classifiers inspired by the statistical perspective in generative or discriminative models are more effective than existing approaches, such as a normality score from a surrogate classifier. We thoroughly evaluate different self-supervised representation learning algorithms under the proposed framework for one-class classification. Moreover, we present a novel distribution-augmented contrastive learning that extends training distributions via data augmentation to obstruct the uniformity of contrastive representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks, including novelty and anomaly detection. Finally, we present visual explanations, confirming that the decision-making process of deep one-class classifiers is intuitive to humans. The code is available at https://github.com/google-research/deep_representation_one_class.
Forward citations
Cited by 5 Pith papers
-
CFR-Net:Collaborative Feature Refinement Network for Medical Image Anomaly Detection
Shared multi-path refinement of teacher and student features plus variance-weighted cross-space consistency yields strong medical anomaly localization under normal-only training.
-
HomographyAD: Deep Anomaly Detection Using Self Homography Learning
Input alignment plus self-supervised homography regression fine-tuning improves pretrained-feature anomaly detection on MVTec object classes, but hurts texture classes.
-
Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
A contrastive anomaly detector trained on pseudo-anomalies and opposite-pair repulsion raises average robust AUROC under PGD-1000 from 39.7% (best prior) to 65.8%.
-
MEATRD: Multimodal Anomalous Tissue Region Detection Enhanced with Spatial Transcriptomics
A multimodal method that fuses histology images and spatial transcriptomics detects anomalous tissue regions better than single-modality and existing multimodal anomaly detectors.
-
Flow-Based Detection and Identification of Zero-Day IoT Cameras
A flow-based ML system reports over 99% accuracy for known IoT camera identification and claims strong zero-day camera detection, but feature-selection leakage and unreleased data weaken the zero-day evidence.
Discussion (0). Continue with ORCID to comment.