Contextually Constrained Deep Networks for Scene Labeling
| Autor: | Taygun Kekec, Elisa Fromont, Christian Wolf, Rémi Emonet, Alain Trémeau |
|---|---|
| Přispěvatelé: | Laboratoire Hubert Curien [Saint Etienne] (LHC), Institut d'Optique Graduate School (IOGS)-Université Jean Monnet [Saint-Étienne] (UJM)-Centre National de la Recherche Scientifique (CNRS), Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), ANR-13-BS02-0002,SoLStiCe,Similarités entre données localement structurées pour la vision par ordinateur(2013), Laboratoire Hubert Curien (LHC), Institut d'Optique Graduate School (IOGS)-Université Jean Monnet - Saint-Étienne (UJM)-Centre National de la Recherche Scientifique (CNRS), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Iterative and incremental development
Optimization problem Computer science business.industry Deep learning Overfitting [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] Machine learning computer.software_genre Constraint (information theory) Local optimum [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Feature (machine learning) Artificial intelligence business computer Interpretability |
| Zdroj: | Proceedings British Machine Vision Conference 2014 British Machine Vision Conference, 2014 British Machine Vision Conference, 2014, Sep 2014, Nottingham, United Kingdom BMVC HAL |
| Popis: | International audience; Learning using deep learning architectures is a difficult problem: the complexity of the prediction model and the difficulty of solving non-convex optimization problems inherent to most learning algorithms can both lead to overfitting phenomena and bad local optima. To overcome these problems we would like to constraint parts of the network using some semantic context to 1) control its capacity while still allowing complex functions to be learned 2) obtain more meaningful layers. We first propose to learn a weak convolutional network which would provide us rough label maps over the neighborhood of a pixel. Then, we incorporate this weak learner in a bigger network. This iterative process aims at increasing the interpretability by constraining some feature maps to learn precise contextual information. Using Stanford and SIFT Flow scene labeling datasets, we show how this contextual knowledge improves accuracy of state-of-the-art architectures. The approach is generic and can be applied to similar networks where contextual cues are available at training time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|