While federated learning traditionally aims to train a single global mod...
Video-to-video synthesis (vid2vid) aims for converting high-level semant...
Conventional CNNs for texture synthesis consist of a sequence of
(de)-co...
Multi-scale inference is commonly used to improve the results of semanti...
Semantic segmentation requires large amounts of pixel-wise annotations t...
In this paper, we present a simple yet effective padding scheme that can...