Abstract | ||
---|---|---|
Neural Network is a powerful Machine Learning tool that shows outstanding performance in Computer Vision, Natural Language Processing, and Artificial Intelligence. In particular, recently proposed ResNet architecture and its modifications produce state-of-the-art results in image classification problems. ResNet and most of the previously proposed architectures have a fixed structure and apply the same transformation to all input images. In this work, we develop a ResNet-based model that dynamically selects Computational Units (CU) for each input object from a learned set of transformations. Dynamic selection allows the network to learn a sequence of useful transformations and apply only required units to predict the image label. We compare our model to ResNet-38 architecture and achieve better results than the original ResNet on CIFAR-10.1 test set. While examining the produced paths, we discovered that the network learned different routes for images from different classes and similar routes for similar images. |
Year | Venue | DocType |
---|---|---|
2018 | ACML | Conference |
Volume | ISSN | Citations |
abs/1811.04380 | Proceedings of The 10th Asian Conference on Machine Learning, PMLR
95:422-437, 2018 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Iurii Kemaev | 1 | 0 | 0.68 |
Daniil Polykovskiy | 2 | 4 | 2.07 |
Dmitry Vetrov | 3 | 263 | 21.56 |