Self-Supervised Class Incremental Learning

11/18/2021
by   Zixuan Ni, et al.
0

Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time, which discards data labels and the model's classifiers. To comprehensively discuss the difference in performance between supervised and self-supervised methods in CIL, we set up three different class incremental schemes: Random Class Scheme, Semantic Class Scheme, and Cluster Scheme, to simulate various class incremental learning scenarios. Besides, we propose Linear Evaluation Protocol (LEP) and Generalization Evaluation Protocol (GEP) to metric the model's representation classification ability and generalization in CIL. Our experiments (on ImageNet-100 and ImageNet) show that SSCIL has better anti-forgetting ability and robustness than supervised strategies in CIL. To understand what alleviates the catastrophic forgetting in SSCIL, we study the major components of SSCIL and conclude that (1) the composition of different data augmentation improves the quality of the model's representation and the Grayscale operation reduces the system noise of data augmentation in SSCIL. (2) the projector, like a buffer, reduces unnecessary parameter updates of the model in SSCIL and increases the robustness of the model. Although the performance of SSCIL is significantly higher than supervised methods in CIL, there is still an apparent gap with joint learning. Our exploration gives a baseline of self-supervised class incremental learning on large-scale datasets and contributes some forward strategies for mitigating the catastrophic forgetting in CIL.

READ FULL TEXT
research
06/10/2020

Self-Supervised Learning Aided Class-Incremental Lifelong Learning

Lifelong or continual learning remains to be a challenge for artificial ...
research
07/05/2023

S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning

Few-shot class-incremental learning (FSCIL) aims to learn progressively ...
research
08/22/2023

An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning

Class-Incremental Learning (CIL) aims to build classification models fro...
research
02/18/2021

Essentials for Class Incremental Learning

Contemporary neural networks are limited in their ability to learn from ...
research
02/26/2023

Knowledge Restore and Transfer for Multi-label Class-Incremental Learning

Current class-incremental learning research mainly focuses on single-lab...
research
10/25/2022

On Robust Incremental Learning over Many Multilingual Steps

Recent work in incremental learning has introduced diverse approaches to...
research
11/05/2022

Local Manifold Augmentation for Multiview Semantic Consistency

Multiview self-supervised representation learning roots in exploring sem...

Please sign up or login with your details

Forgot password? Click here to reset