Learning High-Resolution representations is essential for semantic segmentation. Convolutional neural network (CNN)architectures with downstream and upstream propagation flow are popular for segmentation in medical diagnosis. However, due to performing spatial downsampling and upsampling in multiple stages, information loss is inexorable. On the contrary, connecting layers densely on high spatial resolution is computationally expensive. In this work, we devise a Loose Dense Connection Strategy to connect neurons in subsequent layers with reduced parameters. On top of that, using a m-way Tree structure for feature propagation we propose Receptive Field Chain Network (RFC-Net) that learns high resolution global features on a compressed computational space. Our experiments demonstrates that RFC-Net achieves state-of-the-art performance on Kvasir and CVC-ClinicDB benchmarks for Polyp segmentation.
@article{arxiv.2302.06134,
title = {RFC-Net: Learning High Resolution Global Features for Medical Image Segmentation on a Computational Budget},
author = {Sourajit Saha and Shaswati Saha and Md Osman Gani and Tim Oates and David Chapman},
journal= {arXiv preprint arXiv:2302.06134},
year = {2023}
}
Comments
In Proceedings of AAAI Conference on Artificial Intelligence 2023