Efficacy of Pixel-Level OOD Detection for Semantic Segmentation

Abstract

The detection of out of distribution samples for image classification has been widely researched. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing the image to be out of distribution. This paper adapts state-of-the-art methods for detecting out of distribution images for image classification to the new task of detecting out of distribution pixels, which can localise the unusual objects. It further experimentally compares the adapted methods on two new datasets derived from existing semantic segmentation datasets using PSPNet and DeeplabV3+ architectures, as well as proposing a new metric for the task. The evaluation shows that the performance ranking of the compared methods does not transfer to the new task and every method performs significantly worse than their image-level counterparts.

References in corpus (9)

• The Cityscapes Dataset for Semantic Urban Scene Understanding
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• Deep Anomaly Detection with Outlier Exposure
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
• Discriminative out-of-distribution detection for semantic segmentation
• CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
• IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments

Cited by in corpus (3)

• SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural Networks