CPWC: Contextual Point Wise Convolution for Object Recognition

Pratik Mazumder, Pravendra Singh, Vinay Namboodiri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)
5 Downloads (Pure)

Abstract

Convolutional layers are a major driving force behind the successes of deep learning. Pointwise convolution (PWC) is a 1 × 1 convolutional filter that is primarily used for parameter reduction. However, the PWC ignores the spatial information around the points it is processing. This design is by choice, in order to reduce the overall parameters and computations. However, we hypothesize that this shortcoming of PWC has a significant impact on the network performance. We propose an alternative design for pointwise convolution, which uses spatial information from the input efficiently. Our design significantly improves the performance of the networks without substantially increasing the number of parameters and computations. We experimentally show that our design results in significant improvement in the performance of the network for classification as well as detection.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherIEEE
Pages4152-4156
Number of pages5
ISBN (Electronic)9781509066315
DOIs
Publication statusE-pub ahead of print - 14 May 2020
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: 4 May 20208 May 2020

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
CountrySpain
CityBarcelona
Period4/05/208/05/20

Keywords

  • convolutional neural network
  • deep learning
  • object recognition
  • Pointwise convolution

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'CPWC: Contextual Point Wise Convolution for Object Recognition'. Together they form a unique fingerprint.

Cite this