Learning Disentangled Representations via Mutual Information Estimation
| Autor: | Mathias Ortner, Eduardo Hugo Sanchez, Mathieu Serrurier |
|---|---|
| Přispěvatelé: | Argumentation, Décision, Raisonnement, Incertitude et Apprentissage (IRIT-ADRIA), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, IRT Saint Exupéry - Institut de Recherche Technologique, Airbus Defence and Space [Toulouse] |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Representation disentanglement Computer Science - Machine Learning Theoretical computer science 010504 meteorology & atmospheric sciences Contextual image classification Computer science Specific-information Representation (systemics) Machine Learning (stat.ML) Maximization Mutual information 010501 environmental sciences 01 natural sciences Representation learning Machine Learning (cs.LG) [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] Statistics - Machine Learning Component (UML) Mutual information maximization and minimization Image retrieval Feature learning 0105 earth and related environmental sciences |
| Zdroj: | ECCV 2020: Computer Vision 16th European Conference on Computer Vision-ECCV 2020 16th European Conference on Computer Vision-ECCV 2020, Aug 2020, online, France. pp.205-221, ⟨10.1007/978-3-030-58542-6_13⟩ Computer Vision – ECCV 2020 ISBN: 9783030585419 ECCV (22) |
| DOI: | 10.1007/978-3-030-58542-6_13⟩ |
| Popis: | ISBN 978-3-030-58541-9; International audience; In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation that captures the common information between the images and an exclusive representation that contains the specific information of each image. To address this issue, we propose a model based on mutual information estimation without relying on image reconstruction or image generation. Mutual information maximization is performed to capture the attributes of data in the shared and exclusive representations while we minimize the mutual information between the shared and exclusive representation to enforce representation disentanglement. We show that these representations are useful to perform downstream tasks such as image classification and image retrieval based on the shared or exclusive component. Moreover, classification results show that our model outperforms the state-of-the-art model based on VAE/GAN approaches in representation disentanglement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|