Skip to Main content Skip to Navigation
Conference papers

Adaptative Inference Cost With Convolutional Neural Mixture Models

Adrià Ruiz 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 outstanding performance of convolutional neural networks (CNNs) for many vision tasks, the required computational cost during inference is problematic when resources are limited. In this context, we propose Convolutional Neural Mixture Models (CNMMs), a probabilistic model embedding a large number of CNNs that can be jointly trained and evaluated in an efficient manner. Within the proposed framework, we present different mechanisms to prune subsets of CNNs from the mixture, allowing to easily adapt the computational cost required for inference. Image classification and semantic segmentation experiments show that our method achieve excellent accuracy-compute trade-offs. Moreover, unlike most of previous approaches, a single CNMM provides a large range of operating points along this trade-off, without any re-training.
Complete list of metadata

Cited literature [63 references]  Display  Hide  Download
Contributor : Adrià Ruiz Connect in order to contact the contributor
Submitted on : Monday, August 19, 2019 - 2:27:21 PM
Last modification on : Saturday, June 25, 2022 - 8:29:39 PM
Long-term archiving on: : Thursday, January 9, 2020 - 3:53:34 PM


Files produced by the author(s)




Adrià Ruiz, Jakob Verbeek. Adaptative Inference Cost With Convolutional Neural Mixture Models. ICCV 2019 - International Conference on Computer Vision, Oct 2019, Seoul, South Korea. pp.1872-1881, ⟨10.1109/ICCV.2019.00196⟩. ⟨hal-02267564⟩



Record views


Files downloads