2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | MLR-APPL-IP-6.12 | ||
| Paper Title | GEOMETRIC DATA AUGMENTATION BASED ON FEATURE MAP ENSEMBLE | ||
| Authors | Takashi Shibata, NTT, Japan; Masayuki Tanaka, Masatoshi Okutomi, Tokyo Institute of Technolgy, Japan | ||
| Session | MLR-APPL-IP-6: Machine learning for image processing 6 | ||
| Location | Area E | ||
| Session Time: | Tuesday, 21 September, 15:30 - 17:00 | ||
| Presentation Time: | Tuesday, 21 September, 15:30 - 17:00 | ||
| Presentation | Poster | ||
| Topic | Applications of Machine Learning: Machine learning for image processing | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | 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, CUB2011, and Mnist-rot-12k. | ||