Learning Deep Features for One-Class Classification

01/16/2018
by   Pramuditha Perera, et al.
0

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.

READ FULL TEXT

page 5

page 8

page 10

page 11

research
01/24/2019

One-Class Convolutional Neural Network

We present a novel Convolutional Neural Network (CNN) based approach for...
research
03/06/2019

Deep Transfer Learning for Multiple Class Novelty Detection

We propose a transfer learning-based solution for the problem of multipl...
research
03/04/2019

Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier

Active authentication refers to the process in which users are unobtrusi...
research
05/17/2021

DOC3-Deep One Class Classification using Contradictions

This paper introduces the notion of learning from contradictions (a.k.a ...
research
02/03/2022

SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control

We present a novelty detection framework for Convolutional Neural Networ...
research
03/17/2022

Optimal Rejection Function Meets Character Recognition Tasks

In this paper, we propose an optimal rejection method for rejecting ambi...
research
03/30/2020

OCmst: One-class Novelty Detection using Convolutional Neural Network and Minimum Spanning Trees

We present a novel model called One Class Minimum Spanning Tree (OCmst) ...

Please sign up or login with your details

Forgot password? Click here to reset