Adversarial Structure Matching for Structured Prediction Tasks
CVPR, pp. 4056-4065, 2019.
Pixel-wise losses, e.g., cross-entropy or L2, have been widely used in structured prediction tasks as a spatial extension of generic image classification or regression. However, its i.i.d. assumption neglects the structural regularity present in natural images. Various attempts have been made to incorporate structural reasoning mostly t...More
PPT (Upload PPT)