Feature Embedding by Template Matching as a ResNet Block
Ada Gorgun (Middle East Technical University),* Yeti Z. Gurbuz (Middle East Technical University), Aydin Alatan (Middle East Technical University, Turkey)
The 33rd British Machine Vision Conference
Abstract
Convolution blocks serve as local feature extractors and are the key to success of the neural networks. To make local semantic feature embedding rather explicit, we reformulate convolution blocks as feature selection according to the best matching kernel. In this manner, we show that typical ResNet blocks indeed perform local feature embedding via template matching once batch normalization (BN) followed by a rectified linear unit (ReLU) is interpreted as arg-max optimizer. Following this perspective, we tailor a residual block that explicitly forces semantically meaningful local feature embedding through using label information. Specifically, we assign a feature vector to each local region according to the classes that the corresponding region matches. We evaluate our method on three popular benchmark datasets with several architectures for image classification and consistently show that our approach substantially improves the performance of the baseline architectures.Video
Citation
@inproceedings{Gorgun_2022_BMVC,
author = {Ada Gorgun and Yeti Z. Gurbuz and Aydin Alatan},
title = {Feature Embedding by Template Matching as a ResNet Block},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0225.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by