Connective Reconstruction-based Novelty Detection

TL;DR

This paper introduces Connective Novelty Detection, a reconstruction-based method that combines autoencoder reconstruction errors with generated samples to improve out-of-distribution sample detection in computer vision, outperforming GAN-based approaches.

Contribution

The paper proposes a novel approach that integrates reconstruction error and generated samples in a simple, effective model for out-of-distribution detection, avoiding GAN training issues.

Findings

Significant improvement over state-of-the-art on MNIST and Caltech-256.

Effective combination of real and generated samples enhances detection accuracy.

Robustness to reconstruction error demonstrated in experiments.

Abstract

Detection of out-of-distribution samples is one of the critical tasks for real-world applications of computer vision. The advancement of deep learning has enabled us to analyze real-world data which contain unexplained samples, accentuating the need to detect out-of-distribution instances more than before. GAN-based approaches have been widely used to address this problem due to their ability to perform distribution fitting; however, they are accompanied by training instability and mode collapse. We propose a simple yet efficient reconstruction-based method that avoids adding complexities to compensate for the limitations of GAN models while outperforming them. Unlike previous reconstruction-based works that only utilize reconstruction error or generated samples, our proposed method simultaneously incorporates both of them in the detection task. Our model, which we call "Connective Novelty Detection" has two subnetworks, an autoencoder, and a binary classifier. The autoencoder learns the representation of the positive class by reconstructing them. Then, the model creates negative and connected positive examples using real and generated samples. Negative instances are generated via manipulating the real data, so their distribution is close to the positive class to achieve a more accurate boundary for the classifier. To boost the robustness of the detection to reconstruction error, connected positive samples are created by combining the real and generated samples. Finally, the binary classifier is trained using connected positive and negative examples. We demonstrate a considerable improvement in novelty detection over state-of-the-art methods on MNIST and Caltech-256 datasets.