Deep competitive pathway networks

Jia Ren Chang, Yong Sheng Chen

Research output: Contribution to journalConference articlepeer-review

Abstract

In the design of deep neural architectures, recent studies have demonstrated the benefits of grouping subnetworks into a larger network. For examples, the Inception architecture integrates multi-scale subnetworks and the residual network can be regarded that a residual unit combines a residual subnetwork with an identity shortcut. In this work, we embrace this observation and propose the Competitive Pathway Network (CoPaNet). The CoPaNet comprises a stack of competitive pathway units and each unit contains multiple parallel residual-type subnetworks followed by a max operation for feature competition. This mechanism enhances the model capability by learning a variety of features in subnetworks. The proposed strategy explicitly shows that the features propagate through pathways in various routing patterns, which is referred to as pathway encoding of category information. Moreover, the cross-block shortcut can be added to the CoPaNet to encourage feature reuse. We evaluated the proposed CoPaNet on four object recognition benchmarks: CIFAR-10, CIFAR-100, SVHN, and ImageNet. CoPaNet obtained the state-of-the-art or comparable results using similar amounts of parameters. The code of CoPaNet is available at: https://github.com/JiaRenChang/CoPaNet.

Original languageEnglish
Pages (from-to)264-278
Number of pages15
JournalJournal of Machine Learning Research
Volume77
StatePublished - 1 Jan 2017
Event9th Asian Conference on Machine Learning, ACML 2017 - Seoul, Korea, Republic of
Duration: 15 Nov 201717 Nov 2017

Keywords

  • CNN
  • Competitive mechanism
  • Object recognition

Fingerprint Dive into the research topics of 'Deep competitive pathway networks'. Together they form a unique fingerprint.

Cite this