Convolutional Neural Fabrics

Shreyas Saxena 1 Jakob Verbeek 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/hal-01359150
Contributor : Thoth Team <>
Submitted on : Monday, January 30, 2017 - 1:41:46 PM
Last modification on : Thursday, February 7, 2019 - 4:31:23 PM

File

FabNet_plus_supp_HAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01359150, version 3

Collections

Citation

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

Share

Metrics

Record views

944

Files downloads

428