Few-Shot Class Incremental Learning via Robust Transformer Approach

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Paeedeh, Naeem, Pratama, Mahardhika, Wibirama, Sunu, Mayer, Wolfgang, Cao, Zehong, Kowalczyk, Ryszard
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909197379043328
author Paeedeh, Naeem
Pratama, Mahardhika
Wibirama, Sunu
Mayer, Wolfgang
Cao, Zehong
Kowalczyk, Ryszard
author_facet Paeedeh, Naeem
Pratama, Mahardhika
Wibirama, Sunu
Mayer, Wolfgang
Cao, Zehong
Kowalczyk, Ryszard
contents Few-Shot Class-Incremental Learning presents an extension of the Class Incremental Learning problem where a model is faced with the problem of data scarcity while addressing the catastrophic forgetting problem. This problem remains an open problem because all recent works are built upon the convolutional neural networks performing sub-optimally compared to the transformer approaches. Our paper presents Robust Transformer Approach built upon the Compact Convolution Transformer. The issue of overfitting due to few samples is overcome with the notion of the stochastic classifier, where the classifier's weights are sampled from a distribution with mean and variance vectors, thus increasing the likelihood of correct classifications, and the batch-norm layer to stabilize the training process. The issue of CF is dealt with the idea of delta parameters, small task-specific trainable parameters while keeping the backbone networks frozen. A non-parametric approach is developed to infer the delta parameters for the model's predictions. The prototype rectification approach is applied to avoid biased prototype calculations due to the issue of data scarcity. The advantage of ROBUSTA is demonstrated through a series of experiments in the benchmark problems where it is capable of outperforming prior arts with big margins without any data augmentation protocols.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05984
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Few-Shot Class Incremental Learning via Robust Transformer Approach
Paeedeh, Naeem
Pratama, Mahardhika
Wibirama, Sunu
Mayer, Wolfgang
Cao, Zehong
Kowalczyk, Ryszard
Machine Learning
Artificial Intelligence
Few-Shot Class-Incremental Learning presents an extension of the Class Incremental Learning problem where a model is faced with the problem of data scarcity while addressing the catastrophic forgetting problem. This problem remains an open problem because all recent works are built upon the convolutional neural networks performing sub-optimally compared to the transformer approaches. Our paper presents Robust Transformer Approach built upon the Compact Convolution Transformer. The issue of overfitting due to few samples is overcome with the notion of the stochastic classifier, where the classifier's weights are sampled from a distribution with mean and variance vectors, thus increasing the likelihood of correct classifications, and the batch-norm layer to stabilize the training process. The issue of CF is dealt with the idea of delta parameters, small task-specific trainable parameters while keeping the backbone networks frozen. A non-parametric approach is developed to infer the delta parameters for the model's predictions. The prototype rectification approach is applied to avoid biased prototype calculations due to the issue of data scarcity. The advantage of ROBUSTA is demonstrated through a series of experiments in the benchmark problems where it is capable of outperforming prior arts with big margins without any data augmentation protocols.
title Few-Shot Class Incremental Learning via Robust Transformer Approach
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.05984