Integrating Multiple Receptive Fields Through Grouped Active Convolution

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 37
  • Download : 0
Convolutional networks have achieved great success in various vision tasks. This is mainly due to a considerable amount of research on network structure. In this study, instead of focusing on architectures, we focused on the convolution unit itself. The existing convolution unit has a fixed shape and is limited to observing restricted receptive fields. In earlier work, we proposed the active convolution unit (ACU), which can freely define its shape and learn by itself. In this paper, we provide a detailed analysis of the previously proposed unit and show that it is an efficient representation of a sparse weight convolution. Furthermore, we extend an ACU to a grouped ACU, which can observe multiple receptive fields in one layer. We found that the performance of a naive grouped convolution is degraded by increasing the number of groups; however, the proposed unit retains the accuracy even though the number of parameters decreases. Based on this result, we suggest a depthwise ACU (DACU), and various experiments have shown that our unit is efficient and can replace the existing convolutions.
Publisher
IEEE COMPUTER SOC
Issue Date
2021-11
Language
English
Article Type
Article
Citation

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.43, no.11, pp.3892 - 3903

ISSN
0162-8828
DOI
10.1109/TPAMI.2020.2995864
URI
http://hdl.handle.net/10203/288223
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0