DualMix: Unleashing the Potential of Data Augmentation for Online Class-Incremental Learning

by   Yunfeng Fan, et al.

Online Class-Incremental (OCI) learning has sparked new approaches to expand the previously trained model knowledge from sequentially arriving data streams with new classes. Unfortunately, OCI learning can suffer from catastrophic forgetting (CF) as the decision boundaries for old classes can become inaccurate when perturbated by new ones. Existing literature have applied the data augmentation (DA) to alleviate the model forgetting, while the role of DA in OCI has not been well understood so far. In this paper, we theoretically show that augmented samples with lower correlation to the original data are more effective in preventing forgetting. However, aggressive augmentation may also reduce the consistency between data and corresponding labels, which motivates us to exploit proper DA to boost the OCI performance and prevent the CF problem. We propose the Enhanced Mixup (EnMix) method that mixes the augmented samples and their labels simultaneously, which is shown to enhance the sample diversity while maintaining strong consistency with corresponding labels. Further, to solve the class imbalance problem, we design an Adaptive Mixup (AdpMix) method to calibrate the decision boundaries by mixing samples from both old and new classes and dynamically adjusting the label mixing ratio. Our approach is demonstrated to be effective on several benchmark datasets through extensive experiments, and it is shown to be compatible with other replay-based techniques.


page 1

page 2

page 3

page 4


Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Features

Non-exemplar class-incremental learning refers to classifying new and ol...

Class-Incremental Lifelong Learning in Multi-Label Classification

Existing class-incremental lifelong learning studies only the data is wi...

Data Interpolating Prediction: Alternative Interpretation of Mixup

Data augmentation by mixing samples, such as Mixup, has widely been used...

Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning

Class incremental learning (CIL) aims to incrementally update a trained ...

Label Mapping Neural Networks with Response Consolidation for Class Incremental Learning

Class incremental learning refers to a special multi-class classificatio...

Memory Efficient Class-Incremental Learning for Image Classification

With the memory-resource-limited constraints, class-incremental learning...

An overview of mixing augmentation methods and augmentation strategies

Deep Convolutional Neural Networks have made an incredible progress in m...

Please sign up or login with your details

Forgot password? Click here to reset