Detection of False Positive and False Negative Samples in Semantic Segmentation
This work addresses the need for reliable error detection in automated systems, but it is incremental as it reviews existing techniques rather than proposing new ones.
The paper tackles the problem of handling failure modes in deep learning for safety-critical applications like medical imaging and autonomous driving by reviewing techniques for self-monitoring through uncertainty quantification in semantic segmentation, focusing on detecting false positive and false negative errors at the instance level.
In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation of medical images or autonomous driving. The passage from assistance of a human decision maker to ever more automated systems however increases the need to properly handle the failure modes of deep learning modules. In this contribution, we review a set of techniques for the self-monitoring of machine-learning algorithms based on uncertainty quantification. In particular, we apply this to the task of semantic segmentation, where the machine learning algorithm decomposes an image according to semantic categories. We discuss false positive and false negative error modes at instance-level and review techniques for the detection of such errors that have been recently proposed by the authors. We also give an outlook on future research directions.