Log In Sign Up

Active Class Incremental Learning for Imbalanced Datasets

by   Eden Belouadah, et al.

Incremental Learning (IL) allows AI systems to adapt to streamed data. Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1) new data are assumed to be readily annotated when streamed and (2) tests are run with balanced datasets while most real-life datasets are actually imbalanced. These hypotheses are discarded and the resulting challenges are tackled with a combination of active and imbalanced learning. We introduce sample acquisition functions which tackle imbalance and are compatible with IL constraints. We also consider IL as an imbalanced learning problem instead of the established usage of knowledge distillation against catastrophic forgetting. Here, imbalance effects are reduced during inference through class prediction scaling. Evaluation is done with four visual datasets and compares existing and proposed sample acquisition functions. Results indicate that the proposed contributions have a positive effect and reduce the gap between active and standard IL performance.


page 1

page 2

page 3

page 4


A Comparative Study of Calibration Methods for Imbalanced Class Incremental Learning

Deep learning approaches are successful in a wide range of AI problems a...

Minority Class Oriented Active Learning for Imbalanced Datasets

Active learning aims to optimize the dataset annotation process when res...

A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks

The ability of artificial agents to increment their capabilities when co...

Balanced Split: A new train-test data splitting strategy for imbalanced datasets

Classification data sets with skewed class proportions are called imbala...

R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning

Class-Incremental Learning (CIL) struggles with catastrophic forgetting ...

Effective Decision Boundary Learning for Class Incremental Learning

Rehearsal approaches in class incremental learning (CIL) suffer from dec...

ImDrug: A Benchmark for Deep Imbalanced Learning in AI-aided Drug Discovery

The last decade has witnessed a prosperous development of computational ...