Ferianc, Martin; Manocha, Divyansh; Fan, Hongxiang; Rodrigues, Miguel; (2021) ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation. In: Farkaš, I and Masulli, P and Otte, S and Wermter, S, (eds.) Artificial Neural Networks and Machine Learning – ICANN 2021. (pp. pp. 483-494). Springer Nature: Cham, Switzerland.

Preview

Text 2104.06957v2.pdf - Accepted Version Download (1MB) | Preview

Abstract

Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack uncertainty quantification that may be crucial to many decision-making systems; 2) Large memory storage and computational consumption demanding extensive hardware resources. To address these issues and improve their practicality we demonstrate a few-parameter compact Bayesian convolutional architecture, that achieves a marginal improvement in accuracy in comparison to related work using significantly fewer parameters and compute operations. The architecture combines parameter-efficient operations such as separable convolutions, bilinear interpolation, multi-scale feature propagation and Bayesian inference for per-pixel uncertainty quantification through Monte Carlo Dropout. The best performing configurations required fewer than 2.5 million parameters on diverse challenging datasets with few observations.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item