REVIEW 2 cited by
Learning Deep Features for 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 propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while maintaining a low intra-class variance in the feature space for the given class. For this purpose two loss functions, compactness loss and descriptiveness loss are proposed along with a parallel CNN architecture. A template matching-based framework is introduced to facilitate the testing process. Extensive experiments on publicly available anomaly detection, novelty detection and mobile active authentication datasets show that the proposed Deep One-Class (DOC) classification method achieves significant improvements over the state-of-the-art.
Forward citations
Cited by 2 Pith papers
-
Multi-stage Deep Classifier Cascades for Open World Recognition
A cascade of deep classifiers detects new classes at test time and increments the model with a one-class leaf per new class, reporting better average performance than three baselines on RF device and Twitter datasets.
-
GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection
GODS encloses one-class data between two orthonormal subspace frames, solved on a Stiefel manifold, claiming state-of-the-art anomaly detection; gradient inconsistencies and missing artifacts undermine the claim.
Discussion (0). Continue with ORCID to comment.