DASGAN trains a segmentation network on semi-automatically labeled CK images via unpaired translation to PD-L1, enabling epithelium segmentation and TC score estimation without serial sections.
Conditional Image Synthesis With Auxiliary Classifier GANs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128x128 resolution image samples exhibiting global coherence. We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models. These analyses demonstrate that high resolution samples provide class information not present in low resolution samples. Across 1000 ImageNet classes, 128x128 samples are more than twice as discriminable as artificially resized 32x32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real ImageNet data.
fields
eess.IV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images
DASGAN trains a segmentation network on semi-automatically labeled CK images via unpaired translation to PD-L1, enabling epithelium segmentation and TC score estimation without serial sections.