Bractivate: Dendritic Branching in Medical Image Segmentation Neural Architecture Search

Leila Abdelrahman

Keywords: Neural Architecture Search, Segmentation, Computer Vision

Abstract:

Researchers manually compose most neural networks through painstaking experimentation.
This process is taxing and explores only a limited subset of possible
architecture. Researchers design architectures to address objectives ranging from low
space complexity to high accuracy through hours of experimentation. Neural architecture
search (NAS) is a thriving field for automatically discovering architectures
achieving these same objectives. Addressing these ever-increasing challenges in
computing, we take inspiration from the brain because it has the most efficient
neuronal wiring of any complex structure; its physiology inspires us to propose
Bractivate, a NAS algorithm inspired by neural dendritic branching. An evolutionary algorithm that adds new skip connection combinations to the most active blocks in the network, propagating salient
information through the network. We apply our methods to lung x-ray, cell nuclei
microscopy, and electron microscopy segmentation tasks to highlight Bractivate's robustness.
Moreover, our ablation studies emphasize dendritic branching's necessity: ablating
these connections leads to significantly lower model performance. We finally
compare our discovered architecture with other state-of-the-art UNet models,
highlighting how efficient skip connections allow Bractivate to achieve comparable
results with substantially lower space and time complexity, proving how
Bractivate balances efficiency with performance. We invite you to work with our
code here: \href{https://tinyurl.com/bractivate}{\textcolor{violet}{https://tinyurl.com/bractivate}}.

One-sentence Summary: Bractivate automatically discovers efficient architecture for medical image segmentation through cognitive-inspired dendritic branching.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=1wSKRTZrUl