Domain Generalization via Universal Non-volume Preserving Models
Abstract
Recognition across domains has recently become an active topic in the research community. However, it has been largely overlooked in the problem of recognition in new unseen domains. Under this condition, the delivered deep network models are unable to be updated, adapted, or fine-tuned. Therefore, recent deep learning techniques, such as domain adaptation, feature transferring, and fine-tuning, cannot be applied. This paper presents a novel approach to the problem of domain generalization in the context of deep learning. The proposed method is evaluated on different datasets in various problems, i.e. (i) digit recognition on MNIST, SVHN, and MNIST-M, (ii) face recognition on Extended Yale-B, CMU-PIE and CMU-MPIE, and (iii) pedestrian recognition on RGB and Thermal image datasets. The experimental results show that our proposed method consistently improves performance accuracy. It can also be easily incorporated with any other CNN frameworks within an end-to-end deep network design for object detection and recognition problems to improve their performance.
Cite
@article{arxiv.1905.13040,
title = {Domain Generalization via Universal Non-volume Preserving Models},
author = {Thanh-Dat Truong and Chi Nhan Duong and Khoa Luu and Minh-Triet Tran and Ngan Le},
journal= {arXiv preprint arXiv:1905.13040},
year = {2020}
}
Comments
Accepted to Computer and Robot Vision 2020. arXiv admin note: substantial text overlap with arXiv:1812.03407