Learning Deep Features for One-Class Classification

By Pramuditha Perera, Vishal M. Patel. IEEE Transactions on Image Processing, 2018

411 citations recorded by the source corpus.

We present a novel deep-learning-based approach for one-class transfer learning in which labeled data from an unrelated task is used for 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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/732c21998e251d64cd58b6a86886ee5907efeaa5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition (2019, background): “There are some variation of open-set recognition by relaxing its formulation in the form of anomaly detection [26], [27], [30] and novelty detection [31], [28] etc, but for this paper we only focus on the general open-set recognition problem.”
Learning One Class Representations for Face Presentation Attack Detection Using Multi-Channel Convolutional Neural Networks (2020, background): “Perera and Patel [22] presented an approach for one-class transfer learning in which labelled data from an unrelated task is used for feature learning.”
Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization (2020, methodology): “This technique helps in a graphical analysis of deep learned features and have been very popularly used in many recent works [64]–[67].”
MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection (2019, background): “The landscape of methods for unsupervised anomaly detection is diverse and many approaches have been suggested to tackle the problem [1, 19].”
Self-Supervised Features Improve Open-World Learning (2021, background): “[18], and [50] adapted maximum-margin one-class networks to learn features that enable anomaly detection.”
You Are What You Do: Hunting Stealthy Malware via Data Provenance Analysis (2020, methodology): “More complex machine learning techniques, such as LSTM [58], Tree-structured LSTM [98], Graph Convolu-tional Networks [64], and One-class Neural Networks [36], [88] could possibly further improve the detection accuracy, yet they may also introduce a higher cost.”
A Unifying Review of Deep and Shallow Anomaly Detection (2020, methodology): “Transfer learning approaches to AD also follow the idea of distilling more domain knowledge into a model, for example, through using and possibly fine-tuning pretrained (supervised) models [139], [142], [334], [426], [541].”
OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations (2019, methodology): “Nevertheless, it has a number of applications including abnormality detection [24],[14] intruder detection [17],[13],[16], bio-medical data processing [20] and imbalance learning [10].”
PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation (2020, methodology): “Similar pre-training has been proposed for one-class classification has been proposed by [21], however they require joint optimization with the original task.”
VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization (2021, background): “This requires specialized approaches to handle data imbalance [22], [23].”
Multiple Class Novelty Detection Under Data Distribution Shift (2020, background): “Many problems such as countering adversarial/trojan/poison attacks [26,25,8,47], detecting novel categories [42,40,7,37,35,39] and out-of-distribution samples [13,24,10,54] etc.”
Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders (2018, background): “For the classiﬁcation problem, a number of approaches have been proposed (Perera and Patel, 2018; Sabokrou et al., 2018).”
Classification-Reconstruction Learning for Open-Set Recognition (2018, methodology): “The deep approaches mainly use autoencoders trained in an unsupervised manner [51], in combination with GMM [53], clustering [1], or one-class learning [29].”
Generative-Discriminative Feature Representations for Open-Set Recognition (2020, neutral): “It is also possible to use one-class classification algorithms[24],[21],[20] to solve open-set recognition by modelling known classes.”