-
36浏览
-
0点赞
-
0收藏
-
0分享
-
0下载
-
0评论
-
引用
期刊论文
Deep Rotation Equivariant Network
Neurocomputing,2018,290():26-33 | 2018年05月17日 | doi.org/10.1016/j.neucom.2018.02.029
Recently, learning equivariant representations has attracted considerable research attention. Dieleman et al. introduce four operations which can be inserted into convolutional neural network to learn deep representations equivariant to rotation. However, feature maps should be copied and rotated four times in each layer in their approach, which causes much running time and memory overhead. In order to address this problem, we propose Deep Rotation Equivariant Network consisting of cycle layers, isotonic layers and decycle layers. Our proposed layers apply rotation transformation on filters rather than feature maps, achieving a speed up of more than 2 times with even less memory overhead. We evaluate DRENs on Rotated MNIST and CIFAR-10 datasets and demonstrate that it can improve the performance of state-of-the-art architectures.
学者未上传该成果的PDF文件,请等待学者更新
本学者其他成果
同领域成果