Experiments on Anomaly Detection in Autonomous Driving by Forward-Backward Style Transfers

Abstract

Great progress has been achieved in the community of autonomous driving in the past few years. As a safety-critical problem, however, anomaly detection is a huge hurdle towards a large-scale deployment of autonomous vehicles in the real world. While many approaches, such as uncertainty estimation or segmentation-based image resynthesis, are extremely promising, there is more to be explored. Especially inspired by works on anomaly detection based on image resynthesis, we propose a novel approach for anomaly detection through style transfer. We leverage generative models to map an image from its original style domain of road traffic to an arbitrary one and back to generate pixelwise anomaly scores. However, our experiments have proven our hypothesis wrong, and we were unable to produce significant results. Nevertheless, we want to share our findings, so that others can learn from our experiments.

arXiv commentDaniel Bogdoll and Meng Zhang contributed equally. Accepted for publication at ICECCME 2022

References in corpus (8)

• Representation Learning with Contrastive Predictive Coding
• Prototypical Contrastive Learning of Unsupervised Representations
• Anomaly Detection in Autonomous Driving: A Survey
• The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
• Description of Corner Cases in Automated Driving: Goals and Challenges
• Ad-datasets: a meta-collection of data sets for autonomous driving
• This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity
• Anomaly scores for generative models

Cited by in corpus (1)

• Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey