Discriminative out-of-distribution detection for semantic segmentation
share
This paper considers dense detection of out-of-distribution pixels. As a baseline, we start from recent image-wide approaches and adapt them for dense prediction at the pixel level. Subsequently, we propose and develop a novel approach based on a suitable discriminatively trained model. Thus we reduce our problem to dense classification of image pixels into either ImageNet content (outliers) or the content of the target dataset (inliers). We train the considered approaches on several road driving datasets and evaluate them on the WildDash test dataset. The experimental results show that the proposed approach outperforms previous work by a wide margin.
READ FULL TEXT
