Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

by   Yujun Shi, et al.

Class Incremental Learning (CIL) aims at learning a multi-class classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous works mainly focus on mitigating forgetting in phases after the initial one. However, we find that improving CIL at its initial phase is also a promising direction. Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance. Motivated by this, we study the difference between a naïvely-trained initial-phase model and the oracle model. Specifically, since one major difference between these two models is the number of training classes, we investigate how such difference affects the model representations. We find that, with fewer training classes, the data representations of each class lie in a long and narrow region; with more training classes, the representations of each class scatter more uniformly. Inspired by this observation, we propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly, thus mimicking the model jointly trained with all classes (i.e., the oracle model). Our CwD is simple to implement and easy to plug into existing methods. Extensive experiments on various benchmark datasets show that CwD consistently and significantly improves the performance of existing state-of-the-art methods by around 1% to 3%. Code will be released.


page 1

page 2

page 3

page 4


DILF-EN framework for Class-Incremental Learning

Deep learning models suffer from catastrophic forgetting of the classes ...

On the Stability-Plasticity Dilemma of Class-Incremental Learning

A primary goal of class-incremental learning is to strike a balance betw...

FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning

Exemplar-free class-incremental learning is very challenging due to the ...

Mnemonics Training: Multi-Class Incremental Learning without Forgetting

Multi-Class Incremental Learning (MCIL) aims to learn new concepts by in...

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

Class-Incremental Learning (CIL) aims to build classification models fro...

Preserving Locality in Vision Transformers for Class Incremental Learning

Learning new classes without forgetting is crucial for real-world applic...

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

Class-incremental learning (CIL) learns a classification model with trai...

Please sign up or login with your details

Forgot password? Click here to reset