VisActive: Visual-concept-based Active Learning for Image Classification under Class Imbalance

doi:10.1145/3617999

VisActive: Visual-concept-based Active Learning for Image Classification under Class Imbalance

2023-11-10

1

OA

AI

DOI：10.1145/3617999

Original request for help

Save

Abstract

En 中文

Active learning methods recommend the most informative images from a large unlabeled dataset for manual labeling. These methods improve the performance of an image classifier while minimizing manual labeling efforts. We propose VisActive, a visual-concept-based active learning method for image classification under class imbalance. VisActive learns a visual concept, a generalized representation that holds the most important image characteristics for class prediction, and then recommends for each class four sets of unlabeled images with different visual concepts to increase the diversity and enlarge the training dataset. Experimental results on four datasets show that VisActive outperforms the state-of-the-art deep active learning methods.

Keywords:

Deep active learning

deep neural network

class imbalance

VisActive: Visual-concept-based Active Learning for Image Classification under Class Imbalance

Abstract

Journal

Organization