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

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.

References in corpus (13)

• Distilling the Knowledge in a Neural Network
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• Using Pre-Training Can Improve Model Robustness and Uncertainty
• Deep Anomaly Detection with Outlier Exposure
• Regularizing Neural Networks by Penalizing Confident Output Distributions
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
• Exploration by Random Network Distillation
• Robustly representing uncertainty in deep neural networks through sampling
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity