Spatially-adaptive filter units for compact and efficient deep neural networks

Domen Tabernik, Matej Kristan, Aleš Leonardis

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
121 Downloads (Pure)

Abstract

Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, which has to be manually set to accommodate a specific task. Standard solutions involve large kernels, down/up-sampling and dilated convolutions. These require testing a variety of dilation and down/up-sampling factors and result in non-compact networks and large number of parameters. We address this issue by proposing a new convolution filter composed of displaced aggregation units (DAU). DAUs learn spatial displacements and adapt the receptive field sizes of individual convolution filters to a given problem, thus reducing the need for hand-crafted modifications. DAUs provide a seamless substitution of convolutional filters in existing state-of-the-art architectures, which we demonstrate on AlexNet, ResNet50, ResNet101, DeepLab and SRN-DeblurNet. The benefits of this design are demonstrated on a variety of computer vision tasks and datasets, such as image classification (ILSVRC 2012), semantic segmentation (PASCAL VOC 2011, Cityscape) and blind image de-blurring (GOPRO). Results show that DAUs efficiently allocate parameters resulting in up to 4× more compact networks in terms of the number of parameters at similar or better performance.

Original languageEnglish
Pages (from-to)2049-2067
Number of pages19
JournalInternational Journal of Computer Vision
Volume128
Issue number8-9
Early online date2 Jan 2020
DOIs
Publication statusPublished - Sep 2020

Keywords

  • Adjustable receptive fields
  • Compact ConvNets
  • Displacement units
  • Efficient ConvNets

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Spatially-adaptive filter units for compact and efficient deep neural networks'. Together they form a unique fingerprint.

Cite this