Apprentissage Profond pour des Prédictions Structurées Efficaces appliqué à la Classification Dense en Vision par Ordinateur

Abstract : In this thesis we propose a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRFs) with Convolutional Neural Networks (CNNs). The starting point of this thesis is the observation that while being of a limited form GCRFs allow us to perform exact Maximum-APosteriori (MAP) inference efficiently. We prefer exactness and simplicity over generality and advocate G-CRF based structured prediction in deep learning pipelines. Our proposed structured prediction methods accomodate (i) exact inference, (ii) both shortand long- term pairwise interactions, (iii) rich CNN-based expressions for the pairwise terms, and (iv) end-to-end training alongside CNNs. We devise novel implementation strategies which allow us to overcome memory and computational challenges
Document type :
Theses
Complete list of metadatas

Cited literature [42 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01812763
Contributor : Abes Star <>
Submitted on : Monday, June 11, 2018 - 6:06:06 PM
Last modification on : Tuesday, April 16, 2019 - 9:40:53 AM
Long-term archiving on : Wednesday, September 12, 2018 - 9:50:59 PM

File

74497_CHANDRA_2018_diffusion.p...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01812763, version 1

Citation

Siddhartha Chandra. Apprentissage Profond pour des Prédictions Structurées Efficaces appliqué à la Classification Dense en Vision par Ordinateur. Autre. Université Paris-Saclay, 2018. Français. ⟨NNT : 2018SACLC033⟩. ⟨tel-01812763⟩

Share

Metrics

Record views

397

Files downloads

625