Skip to Main content Skip to Navigation
New interface
Conference papers

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 metadata

Cited literature [32 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Monday, January 30, 2017 - 1:41:46 PM
Last modification on : Friday, February 4, 2022 - 3:12:15 AM


Files produced by the author(s)


  • HAL Id : hal-01359150, version 3



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



Record views


Files downloads