For the task of semantic segmentation, high-resolution (pixel-level) ground truth is very expensive to collect, especially for high resolution images such as gigapixel pathology images. On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient. Conventional methods trained on these low-resolution labels are only capable of giving low-resolution predictions. The existing state-of-the-art label super resolution (LSR) method is capable of predicting high resolution labels, using only low-resolution supervision, given the joint distribution between low resolution and high resolution labels. However, it does not consider the inter-instance variance which is crucial in the ideal mathematical formulation. In this work, we propose a novel loss function modeling the inter-instance variance. We test our method on a real world application: infiltrating breast cancer region segmentation in histopathology slides. Experimental results show the effectiveness of our method.
@article{arxiv.1904.04429,
title = {Label Super Resolution with Inter-Instance Loss},
author = {Maozheng Zhao and Le Hou and Han Le and Dimitris Samaras and Nebojsa Jojic and Danielle Fassler and Tahsin Kurc and Rajarsi Gupta and Kolya Malkin and Shroyer Kenneth and Joel Saltz},
journal= {arXiv preprint arXiv:1904.04429},
year = {2020}
}