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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kalla, Jayateja, Biswas, Soma
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911982225981440
author Kalla, Jayateja
Biswas, Soma
author_facet Kalla, Jayateja
Biswas, Soma
contents 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 any class-incremental learning framework, leveraging its powerful feature learning capabilities to enhance performance across various class-incremental learning approaches. Extensive experiments conducted on standard incremental learning datasets CIFAR-100 and ImageNet-Subset demonstrate the significant role of AggSS in improving performance within these paradigms.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04347
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AggSS: An Aggregated Self-Supervised Approach for Class-Incremental Learning
Kalla, Jayateja
Biswas, Soma
Computer Vision and Pattern Recognition
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 any class-incremental learning framework, leveraging its powerful feature learning capabilities to enhance performance across various class-incremental learning approaches. Extensive experiments conducted on standard incremental learning datasets CIFAR-100 and ImageNet-Subset demonstrate the significant role of AggSS in improving performance within these paradigms.
title AggSS: An Aggregated Self-Supervised Approach for Class-Incremental Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.04347