| Full text | |
| Author(s): |
Total Authors: 3
|
| Affiliation: | [1] Univ Estadual Campinas, Inst Comp, BR-13083970 Campinas, SP - Brazil
[2] Lisbon Univ, ISTAR IUL Lab, Inst ISCTE IUL, P-1649026 Lisbon - Portugal
[3] IST, P-1649026 Lisbon - Portugal
[4] INESC ID, P-1649026 Lisbon - Portugal
Total Affiliations: 4
|
| Document type: | Journal article |
| Source: | IEEE SIGNAL PROCESSING LETTERS; v. 26, n. 7, p. 1006-1010, JUL 2019. |
| Web of Science Citations: | 0 |
| Abstract | |
We introduce multi-lane capsule networks (MLCN), which are a separable and resource efficient organization of capsule networks (CapsNet) that allows parallel processing while achieving high accuracy at reduced cost. A MLCN is composed of a number of (distinct) parallel lanes, each contributing to a dimension of the result, trained using the routing-by-agreement organization of CapsNet. Our results indicate similar accuracy with a much-reduced cost in number of parameters for the Fashion-MNIST and Cifar10 datasets. They also indicate that the MLCN outperforms the original CapsNet when using a proposed novel configuration for the lanes. MLCN also has faster training and inference times, being more than two-fold faster than the original CapsNet in a same accelerator. (AU) | |
| FAPESP's process: | 13/08293-7 - CCES - Center for Computational Engineering and Sciences |
| Grantee: | Munir Salomao Skaf |
| Support Opportunities: | Research Grants - Research, Innovation and Dissemination Centers - RIDC |