Implicit Background Estimation for Semantic Segmentation
This work addresses robustness issues in semantic segmentation for safety-critical applications like human interaction, but it is incremental as it builds on existing state-of-the-art models.
The paper tackled the problem of improving robustness in semantic segmentation models by correcting non-distinct mappings from the softmax function, resulting in enhanced robustness with minimal performance impact and code changes.
Scene understanding and semantic segmentation are at the core of many computer vision tasks, many of which, involve interacting with humans in potentially dangerous ways. It is therefore paramount that techniques for principled design of robust models be developed. In this paper, we provide analytic and empirical evidence that correcting potentially errant non-distinct mappings that result from the softmax function can result in improving robustness characteristics on a state-of-the-art semantic segmentation model with minimal impact to performance and minimal changes to the code base.