Detecting the Unexpected via Image Resynthesis

ICCV 2019 Krzysztof LisKrishna NakkaPascal FuaMathieu Salzmann

Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes can appear at test time... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.