Compact Surjective Encoding Autoencoder for Unsupervised Novelty Detection

03/03/2020
by   Jaewoo Park, et al.
0

In unsupervised novelty detection, a model is trained solely on the in-class data, and infer to single out out-class data. Autoencoder (AE) variants aim to compactly model the in-class data to reconstruct it exclusively, differentiating it from out-class by the reconstruction error. However, it remains challenging for high-dimensional image data in the fully unsupervised setting. For this, we propose Compact Surjective Encoding AE (CSE-AE). In this framework, the encoding of any input is constrained into a compact manifold by exploiting the deep neural net's ignorance of the unknown. Concurrently, the in-class data is surjectively encoded to the compact manifold via AE. The mechanism is realized by both GAN and its ensembled discriminative layers, and results to reconstruct the in-class exclusively. In inference, the reconstruction error of a query is measured using high-level semantics captured by the discriminator. Extensive experiments on image data show that the proposed model gives state-of-the-art performance.

READ FULL TEXT

page 5

page 8

page 9

page 13

research
01/07/2021

OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space

Novelty detection using deep generative models such as autoencoder, gene...
research
05/02/2023

Representation Learning via Manifold Flattening and Reconstruction

This work proposes an algorithm for explicitly constructing a pair of ne...
research
07/06/2018

Generative Probabilistic Novelty Detection with Adversarial Autoencoders

Novelty detection is the problem of identifying whether a new data point...
research
03/27/2021

OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection

Novelty detection is the task of recognizing samples that do not belong ...
research
11/20/2021

Constrained Deep One-Class Feature Learning For Classifying Imbalanced Medical Images

Medical image data are usually imbalanced across different classes. One-...
research
02/10/2020

Iterative energy-based projection on a normal data manifold for anomaly localization

Autoencoder reconstructions are widely used for the task of unsupervised...
research
03/04/2022

Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection

In some scenarios, classifier requires detecting out-of-distribution sam...

Please sign up or login with your details

Forgot password? Click here to reset