Mahfuzur Rahman Siddiquee

TL;DR: This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.

TL;DR: UNet++ as discussed by the authors is a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways.

TL;DR: UNet++ as mentioned in this paper proposes an efficient ensemble of U-Nets of varying depths, which partially share an encoder and co-learn simultaneously using deep supervision, leading to a highly flexible feature fusion scheme.

TL;DR: The authors' extensive experiments demonstrate that their Models Genesis significantly outperform learning from scratch in all five target 3D applications covering both segmentation and classification, and are attributed to the unified self-supervised learning framework, built on a simple yet powerful observation.

TL;DR: Li et al. as discussed by the authors proposed a fixed-point GAN to identify a minimal subset of target pixels for domain translation, an ability that no GAN is equipped with yet, and trained by supervising same domain translation through a conditional identity loss, and regularizing cross-domain translation through revised adversarial, domain classification, and cycle consistency loss.