Puzzle-AE: Novelty Detection in Images through Solving Puzzles

Abstract

Autoencoder, as an essential part of many anomaly detection methods, is lacking flexibility on normal data in complex datasets. U-Net is proved to be effective for this purpose but overfits on the training data if trained by just using reconstruction error similar to other AE-based frameworks. Puzzle-solving, as a pretext task of self-supervised learning (SSL) methods, has earlier proved its ability in learning semantically meaningful features. We show that training U-Nets based on this task is an effective remedy that prevents overfitting and facilitates learning beyond pixel-level features. Shortcut solutions, however, are a big challenge in SSL tasks, including jigsaw puzzles. We propose adversarial robust training as an effective automatic shortcut removal. We achieve competitive or superior results compared to the State of the Art (SOTA) anomaly detection methods on various toy and real-world datasets. Unlike many competitors, the proposed framework is stable, fast, data-efficient, and does not require unprincipled early stopping.

arXiv commentThe paper is under consideration at Computer Vision and Image Understanding

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• A Survey on Deep Learning in Medical Image Analysis
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Towards Deep Learning Models Resistant to Adversarial Attacks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Deep Learning for Anomaly Detection: A Survey
• Fast is better than free: Revisiting adversarial training
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
• Deep Anomaly Detection Using Geometric Transformations
• Deep Structured Energy Based Models for Anomaly Detection
• On Convergence and Stability of GANs
• Robust PCA via Outlier Pursuit
• Wasserstein Auto-Encoders
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization

Cited by in corpus (3)

• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Visual Anomaly Detection for Images: A Survey
• Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies