One-Class Convolutional Neural Network

Abstract

We present a novel Convolutional Neural Network (CNN) based approach for one class classification. The idea is to use a zero centered Gaussian noise in the latent space as the pseudo-negative class and train the network using the cross-entropy loss to learn a good representation as well as the decision boundary for the given class. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one class classification. The proposed One Class CNN (OC-CNN) is evaluated on the UMDAA-02 Face, Abnormality-1001, FounderType-200 datasets. These datasets are related to a variety of one class application problems such as user authentication, abnormality detection and novelty detection. Extensive experiments demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. The source code is available at : github.com/otkupjnoz/oc-cnn.

References in corpus (2)

• One-Class Classification: Taxonomy of Study and Review of Techniques
• Active User Authentication for Smartphones: A Challenge Data Set and Benchmark Results

Cited by in corpus (15)

• A Unifying Review of Deep and Shallow Anomaly Detection
• Artificial Intelligence based Anomaly Detection of Energy Consumption in Buildings: A Review, Current Trends and New Perspectives
• Learning Deep Features for One-Class Classification
• Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors
• MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
• A One-Class Classification Decision Tree Based on Kernel Density Estimation
• PAD: Towards Principled Adversarial Malware Detection Against Evasion Attacks
• Learning image representations for anomaly detection: application to discovery of histological alterations in drug development
• Interpretable Transformation and Analysis of Timelines through Learning via Surprisability
• Meta Learning for Few-Shot One-class Classification
• Chromosomal Structural Abnormality Diagnosis by Homologous Similarity
• OOD-SEG: Exploiting out-of-distribution detection techniques for learning image segmentation from sparse multi-class positive-only annotations
• SpaNN: Detecting Multiple Adversarial Patches on CNNs by Spanning Saliency Thresholds
• Critical Review for One-class Classification: recent advances and the reality behind them
• Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics