Adapting branched networks to realise progressive intelligence

Jack Dymond (University of Southampton),* Sebastian Stein (University of Southampton), Steve R Gunn (University of Southampton)
The 33rd British Machine Vision Conference


Progressive intelligence is a formulation of machine learning which trades-off performance requirements with resource availability. It does this by approaching the inference process incrementally. Current work in this area focuses on overall model performance rather than optimising its complete operating range. In this paper, we build upon existing explainability and branched neural network research to show how neural networks can be adapted to exhibit progressive intelligence. We assess the utility of joint branch optimisation for progressive intelligence using a number of explainability metrics. When optimising the area under curve of layer- wise linear probe accuracy we find equally weighted early-exit branch optimisation produces models with the highest linear probe accuracy throughout the backbone. By varying confidence thresholds we represent the entire range over which the model can operate, we then explore its interaction with the scaling of the branched neural network backbone. Finally, we propose a novel ensemble inference strategy which utilises repeat predictions and requires no additional optimisation. Experiments with CIFAR10/100 show that this inference strategy can save up to 44% of the multiply ac- cumulate operations used in inference whilst maintaining model performance, when compared against conventional early-exit methods.



author    = {Jack Dymond and Sebastian Stein and Steve R Gunn},
title     = {Adapting branched networks to realise progressive intelligence},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year      = {2022},
url       = {}

Copyright © 2022 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection