AggSS: An Aggregated Self-Supervised Approach for Class Incremental Learning


Jayateja Kalla (Indian Institute of Science), Soma Biswas (Indian Institute of Science, Bangalore, India)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

This paper investigates the impact of self-supervised learning, specifically image rotations, on various class-incremental learning paradigms. Here, each image with a predefined rotation is considered as a new class for training. At inference, all image rotation predictions are aggregated for the final prediction, a strategy we term Aggregated Self-Supervision (AggSS). We observe a shift in the deep neural network's attention towards intrinsic object features as it learns through AggSS strategy. This learning approach significantly enhances class-incremental learning by promoting robust feature learning. AggSS serves as a plug-and-play module that can be seamlessly incorporated into many class-incremental learning frameworks, leveraging its powerful feature learning capabilities to enhance performance across various class-incremental learning approaches. Extensive experiments conducted on standard incremental learning datasets, namely CIFAR-100 and ImageNet-Subset demonstrate the significant role of AggSS in improving performance for these paradigms.

Citation

@inproceedings{Kalla_2024_BMVC,
author    = {Jayateja Kalla and Soma Biswas},
title     = {AggSS: An Aggregated Self-Supervised Approach for Class Incremental Learning},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0689.pdf}
}


Copyright © 2024 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