“Multi-Class Active Learning by Uncertainty Sampling With Diversity Maximization”, Yi Yang, Zhigang Ma, Feiping Nie, Xiaojun Chang, Alexander G. Hauptmann2022-11-09 (active learning)⁠:

As a way to relieve the tedious work of manual annotation, active learning plays important roles in many applications of visual concept recognition. In typical active learning scenarios, the number of labeled data in the seed set is usually small. However, most existing active learning algorithms only exploit the labeled data, which often suffers from overfitting due to the small number of labeled examples. Besides, while much progress has been made in binary class active learning, little research attention has been focused on multi-class active learning.

In this paper, we propose a semi-supervised batch mode multi-class active learning algorithm for visual concept recognition. Our algorithm exploits the whole active pool to evaluate the uncertainty of the data. Considering that uncertain data are always similar to each other, we propose to make the selected data as diverse as possible, for which we explicitly impose a diversity constraint on the objective function. As a multi-class active learning algorithm, our algorithm is able to exploit uncertainty across multiple classes. An efficient algorithm is used to optimize the objective function.

Extensive experiments on action recognition, object classification, scene recognition, and event detection demonstrate its advantages.

In conclusion, this work presents a novel approach towards addressing the challenges in multi-class active learning for visual concept recognition by incorporating diversity and semi-supervised learning strategies to improve performance and reliability.