Z
Zongwei Zhou
Researcher at Arizona State University
Publications - 33
Citations - 7177
Zongwei Zhou is an academic researcher from Arizona State University. The author has contributed to research in topics: Transfer of learning & Deep learning. The author has an hindex of 12, co-authored 31 publications receiving 2588 citations. Previous affiliations of Zongwei Zhou include Arizona's Public Universities.
Papers
More filters
Posted Content
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
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.
Book ChapterDOI
Unet++: A nested u-net architecture for medical image segmentation
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.
Journal ArticleDOI
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
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.
Proceedings ArticleDOI
Fine-Tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally
TL;DR: This paper presents a novel method called AIFT (active, incremental fine-tuning) to naturally integrate active learning and transfer learning into a single framework and demonstrates that the cost of annotation can be cut by at least half.
Book ChapterDOI
Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis.
Zongwei Zhou,Vatsal Sodha,Mahfuzur Rahman Siddiquee,Ruibin Feng,Nima Tajbakhsh,Michael B. Gotway,Jianming Liang +6 more
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.