Label Super Resolution with Inter-Instance Loss

TL;DR

This paper introduces a novel loss function for label super resolution in semantic segmentation, leveraging inter-instance variance to improve high-resolution label prediction from low-resolution supervision, especially in histopathology images.

Contribution

The paper proposes a new loss function that models inter-instance variance, enhancing label super resolution capabilities from low-resolution labels in high-resolution image segmentation.

Findings

Effective in breast cancer histopathology segmentation

Outperforms previous LSR methods on real-world data

Demonstrates significant improvement in high-resolution label prediction

Abstract

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.