Geometric Data Augmentation Based on Feature Map Ensemble

Autor:	Shibata, Takashi, Tanaka, Masayuki, Okutomi, Masatoshi
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawbacks. The performance of CNN is dramatically degraded by geometric transformation, such as large rotations. In this paper, we propose a novel CNN architecture that can improve the robustness against geometric transformations without modifying the existing backbones of their CNNs. The key is to enclose the existing backbone with a geometric transformation (and the corresponding reverse transformation) and a feature map ensemble. The proposed method can inherit the strengths of existing CNNs that have been presented so far. Furthermore, the proposed method can be employed in combination with state-of-the-art data augmentation algorithms to improve their performance. We demonstrate the effectiveness of the proposed method using standard datasets such as CIFAR, CUB-200, and Mnist-rot-12k. Comment: Accepted to ICIP2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2107.10524 Zobrazit plný text záznamu View this record from Arxiv