Dense open-set recognition with synthetic outliers generated by Real NVP
This work tackles the critical problem of out-of-distribution detection for deep learning models, which is crucial for safety-critical applications like healthcare and autonomous driving, offering an incremental improvement over existing methods.
The paper addresses the inability of deep models to detect out-of-distribution inputs, which leads to confident incorrect predictions. It proposes an outlier detection method using discriminative training with synthetic outliers generated by a jointly trained Real NVP model, achieving competitive performance in image classification and semantic segmentation with a single forward pass.
Today's deep models are often unable to detect inputs which do not belong to the training distribution. This gives rise to confident incorrect predictions which could lead to devastating consequences in many important application fields such as healthcare and autonomous driving. Interestingly, both discriminative and generative models appear to be equally affected. Consequently, this vulnerability represents an important research challenge. We consider an outlier detection approach based on discriminative training with jointly learned synthetic outliers. We obtain the synthetic outliers by sampling an RNVP model which is jointly trained to generate datapoints at the border of the training distribution. We show that this approach can be adapted for simultaneous semantic segmentation and dense outlier detection. We present image classification experiments on CIFAR-10, as well as semantic segmentation experiments on three existing datasets (StreetHazards, WD-Pascal, Fishyscapes Lost & Found), and one contributed dataset. Our models perform competitively with respect to the state of the art despite producing predictions with only one forward pass.