Convolutional Neural Fabrics - Archive ouverte HAL Access content directly
Conference Papers Year :

Convolutional Neural Fabrics

(1) , (1)
1

Abstract

Despite the success of CNNs, selecting the optimal architecture for a given task remains an open problem. Instead of aiming to select a single optimal architecture, we propose a " fabric " that embeds an exponentially large number of architectures. The fabric consists of a 3D trellis that connects response maps at different layers, scales, and channels with a sparse homogeneous local connectivity pattern. The only hyper-parameters of a fabric are the number of channels and layers. While individual architectures can be recovered as paths, the fabric can in addition ensemble all embedded architectures together, sharing their weights where their paths overlap. Parameters can be learned using standard methods based on back-propagation, at a cost that scales linearly in the fabric size. We present benchmark results competitive with the state of the art for image classification on MNIST and CIFAR10, and for semantic segmentation on the Part Labels dataset.
Fichier principal
Vignette du fichier
FabNet_plus_supp_HAL.pdf (1.94 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01359150 , version 1 (09-09-2016)
hal-01359150 , version 2 (28-10-2016)
hal-01359150 , version 3 (30-01-2017)

Identifiers

  • HAL Id : hal-01359150 , version 3

Cite

Shreyas Saxena, Jakob Verbeek. Convolutional Neural Fabrics. NIPS - Advances in Neural Information Processing Systems, Dec 2016, Barcelona, Spain. pp.1-9. ⟨hal-01359150v3⟩
1035 View
1052 Download

Share

Gmail Facebook Twitter LinkedIn More