Citation

BibTex format

@inproceedings{Zhang:2024,
author = {Zhang, D and Williams, M and Toni, F},
publisher = {AAAI},
title = {Targeted activation penalties help CNNs ignore spurious signals},
url = {http://hdl.handle.net/10044/1/108884},
year = {2024}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Neural networks (NNs) can learn to rely on spurious signals in the training data, leading to poor generalisation. Recent methods tackle this problem by training NNs with additional ground-truth annotations of such signals. These methods may, however, let spurious signals re-emerge in deep convolutional NNs (CNNs). We propose Targeted Activation Penalty (TAP), a new method tackling the same problem by penalising activations to control the re-emergence of spurious signals in deep CNNs, while also lowering training times and memory usage. In addition, ground-truth annotations can be expensive to obtain. We show that TAP still works well with annotations generated by pre-trained models as effective substitutes of ground-truth annotations. We demonstrate the power of TAP against two state-of-the-art baselines on the MNIST benchmark and on two clinical image datasets, using four different CNN architectures.
AU - Zhang,D
AU - Williams,M
AU - Toni,F
PB - AAAI
PY - 2024///
SN - 2159-5399
TI - Targeted activation penalties help CNNs ignore spurious signals
UR - http://hdl.handle.net/10044/1/108884
ER -

Contact us

Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ

To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk