Long-Tailed Class Incremental Learning

10/01/2022
by   Xialei Liu, et al.
0

In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of long-tailed distributions in the real world. In this work we propose two long-tailed CIL scenarios, which we term ordered and shuffled LT-CIL. Ordered LT-CIL considers the scenario where we learn from head classes collected with more samples than tail classes which have few. Shuffled LT-CIL, on the other hand, assumes a completely random long-tailed distribution for each task. We systematically evaluate existing methods in both LT-CIL scenarios and demonstrate very different behaviors compared to conventional CIL scenarios. Additionally, we propose a two-stage learning baseline with a learnable weight scaling layer for reducing the bias caused by long-tailed distribution in LT-CIL and which in turn also improves the performance of conventional CIL due to the limited exemplars. Our results demonstrate the superior performance (up to 6.44 points in average incremental accuracy) of our approach on CIFAR-100 and ImageNet-Subset. The code is available at https://github.com/xialeiliu/Long-Tailed-CIL

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/15/2023

Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

In this paper, our goal is to design a simple learning paradigm for long...
research
07/19/2022

Invariant Feature Learning for Generalized Long-Tailed Classification

Existing long-tailed classification (LT) methods only focus on tackling ...
research
07/27/2022

Identifying Hard Noise in Long-Tailed Sample Distribution

Conventional de-noising methods rely on the assumption that all samples ...
research
07/04/2022

Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition

Existing out-of-distribution (OOD) detection methods are typically bench...
research
07/20/2021

Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-Supervision

Existing long-tailed recognition methods, aiming to train class-balance ...
research
04/01/2021

Improving Calibration for Long-Tailed Recognition

Deep neural networks may perform poorly when training datasets are heavi...
research
01/26/2021

ResLT: Residual Learning for Long-tailed Recognition

Deep learning algorithms face great challenges with long-tailed data dis...

Please sign up or login with your details

Forgot password? Click here to reset