A Joint Representation Learning and Feature Modeling Approach for One-class Recognition

TL;DR

This paper introduces a novel method combining generative feature learning and adversarial training to improve one-class recognition, achieving state-of-the-art results across multiple tasks.

Contribution

It proposes a joint approach that integrates generative feature learning with feature distribution modeling using adversarial training for one-class recognition.

Findings

Achieved state-of-the-art performance on three one-class classification tasks.

Demonstrated the effectiveness of combining generative features with adversarial distribution modeling.

Reduced redundancy in feature space leading to improved recognition accuracy.

Abstract

One-class recognition is traditionally approached either as a representation learning problem or a feature modeling problem. In this work, we argue that both of these approaches have their own limitations; and a more effective solution can be obtained by combining the two. The proposed approach is based on the combination of a generative framework and a one-class classification method. First, we learn generative features using the one-class data with a generative framework. We augment the learned features with the corresponding reconstruction errors to obtain augmented features. Then, we qualitatively identify a suitable feature distribution that reduces the redundancy in the chosen classifier space. Finally, we force the augmented features to take the form of this distribution using an adversarial framework. We test the effectiveness of the proposed method on three one-class classification tasks and obtain state-of-the-art results.