File(s) stored somewhere else
Please note: Linked content is NOT stored on Open Access Victoria University of Wellington | Te Herenga Waka and we can't guarantee its availability, quality, security or accept any liability.
Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning
journal contributionposted on 01.08.2021, 02:47 by Ying BiYing Bi, Bing XueBing Xue, Mengjie ZhangMengjie Zhang
Using evolutionary computation algorithms to solve multiple tasks with knowledge sharing is a promising approach. Image feature learning can be considered as a multitask learning problem because different tasks may have a similar feature space. Genetic programming (GP) has been successfully applied to image feature learning for classification. However, most of the existing GP methods solve one task, independently, using sufficient training data. No multitask GP method has been developed for image feature learning. Therefore, this paper develops a multitask GP approach to image feature learning for classification with limited training data. Owing to the flexible representation of GP, a new knowledge sharing mechanism based on a new individual representation is developed to allow GP to automatically learn what to share across two tasks and to improve its learning performance. The shared knowledge is encoded as a common tree, which can represent the common/general features of two tasks. With the new individual representation, each task is solved using the features extracted from a common tree and a task-specific tree representing task-specific features. To find the best common and task-specific trees, a new evolutionary search process and fitness functions are developed. The performance of the new approach is examined on six multitask learning problems of 12 image classification datasets with limited training data and compared with 17 competitive methods. Experimental results show that the new approach outperforms these comparison methods in almost all the comparisons. Further analysis reveals that the new approach learns simple yet effective common trees with high effectiveness and transferability.