Bridging In- and Out-of-distribution Samples for Their Better Discriminability

2021/01/07 by Engkarat Techapanurak, Techapanurak, Engkarat, Anh-Chuong Dang +3 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2101.02500

openalex publication_date 2021/01/07 · openalex created_date 2021/01/18 · openalex updated_date 2026/07/28

Abstract

This paper proposes a method for OOD detection. Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network. We generate such samples using multiple image transformations that corrupt inputs in various ways and with different severity levels. We estimate where the generated samples by a single image transformation lie between ID and OOD using a network trained on clean ID samples. To be specific, we make the network classify the generated samples and calculate their mean classification accuracy, using which we create a soft target label for them. We train the same network from scratch using the original ID samples and the generated samples with the soft labels created for them. We detect OOD samples by thresholding the entropy of the predicted softmax probability. The experimental results show that our method outperforms the previous state-of-the-art in the standard benchmark tests. We also analyze the effect of the number and particular combinations of image corrupting transformations on the performance.

Citations

• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Distilling the Knowledge in a Neural Network
• TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Exploration by Random Network Distillation
• Deep Anomaly Detection with Outlier Exposure
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Learning Multiple Layers of Features from Tiny Images

Cited by

• BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks

Related

• Raising the Bar on the Evaluation of Out-of-Distribution Detection
• Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need
• SR-OOD: Out-of-Distribution Detection via Sample Repairing
• A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?
• ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms