کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6864231 1439537 2018 8 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Deep Rotation Equivariant Network
ترجمه فارسی عنوان
شبکه متناوب چرخش عمیق
کلمات کلیدی
شبکه عصبی، معادله چرخش، یادگیری عمیق،
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی
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.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 290, 17 May 2018, Pages 26-33
نویسندگان
, , , ,