FlexPooling with Simple Auxiliary Classifiers in Deep Networks

Muhammad Ali, Omar Alsuwaidi, Salman Khan

2023

Abstract

In Computer Vision, the basic pipeline of most convolutional neural networks (CNNs) consists of multiple feature extraction processing layers, wherein the input signal is downsampled into a lower resolution in each subsequent layer. This downsampling process is commonly referred to as pooling, an essential operation in CNNs. It improves the model’s robustness against variances in transformation, reduces the number of trainable parameters, increases the receptive field size, and reduces computation time. Since pooling is a lossy process yet crucial in inferring high-level information from low-level information, we must ensure that each subsequent layer perpetuates the most prominent information from previous activations to aid the network’s discriminability. The standard way to apply this process is to use dense pooling (max or average) or strided convolutional kernels. In this paper, we propose a simple yet effective adaptive pooling method, referred to as FlexPooling, which generalizes the concept of average pooling by learning a weighted average pooling over the activations jointly with the rest of the network. Moreover, attaching the CNN with Simple Auxiliary Classifiers (SAC) further demonstrates the superiority of our method as compared to the standard methods. Finally, we show that our simple approach consistently outperforms baseline networks on multiple popular datasets in image classification, giving us around a 1-3% increase in accuracy.

Paper Citation

in Harvard Style

Ali M., Alsuwaidi O. and Khan S. (2023). FlexPooling with Simple Auxiliary Classifiers in Deep Networks. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 497-505. DOI: 10.5220/0011894400003417

in Bibtex Style

@conference{visapp23,
author={Muhammad Ali and Omar Alsuwaidi and Salman Khan},
title={FlexPooling with Simple Auxiliary Classifiers in Deep Networks},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={497-505},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011894400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - FlexPooling with Simple Auxiliary Classifiers in Deep Networks
SN - 978-989-758-634-7
AU - Ali M.
AU - Alsuwaidi O.
AU - Khan S.
PY - 2023
SP - 497
EP - 505
DO - 10.5220/0011894400003417
PB - SciTePress