Active Class Incremental Learning for Imbalanced Datasets

2020-08-25 · Eden Belouadah, Adrian Popescu, Umang Aggarwal, Léo Saci

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.

📄 PDF Abstract BibTeX arXiv:2008.10968

Code (1)

EdenBelouadah/class-incremental-learning 공식 구현 pytorch

Tasks

class-incremental learning Class Incremental Learning Incremental Learning Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Class Balance Matters to Active Class-Incremental Learning

2024-12-09 · Zitong Huang, Ze Chen, Yuanze Li, Bowen Dong 외

Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may not always cover the most informative sa…

Active Learning class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning+2

Imbalanced Deep Learning by Minority Class Incremental Rectification

2018-04-28 · Qi Dong, Shaogang Gong, Xiatian Zhu

Model learning from class imbalanced training data is a long-standing and significant challenge for machine learning. In particular, existing deep learning methods consider mostly either class balanced data or moderately…

Attribute Deep Learning Facial Attribute Classification

A Comparative Study of Calibration Methods for Imbalanced Class Incremental Learning

2022-02-01 · Umang Aggarwal, Adrian Popescu, Eden Belouadah, Céline Hudelot

Deep learning approaches are successful in a wide range of AI problems and in particular for visual recognition tasks. However, there are still open problems among which is the capacity to handle streams of visual inform…

class-incremental learning Class Incremental Learning Incremental Learning Management

Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Data

2024-06-07 · Sohaib Younis, Bernhard Seeger

Continual learning is a challenging problem in machine learning, especially for image classification tasks with imbalanced datasets. It becomes even more challenging when it involves learning new classes incrementally. O…

class-incremental learning Class Incremental Learning Continual Learning image-classification+3

Minority Class Oriented Active Learning for Imbalanced Datasets

2022-02-01 · Umang Aggarwal, Adrian Popescu, Céline Hudelot

Active learning aims to optimize the dataset annotation process when resources are constrained. Most existing methods are designed for balanced datasets. Their practical applicability is limited by the fact that a majori…

Active Learning Transfer Learning