DURAND Thibaut
Supervision : Matthieu CORD
Co-supervision : THOME Nicolas
Weakly Supervised Learning for Visual Recognition
This thesis studies the problem of the classification of images, where the goal is to predict if a semantic category - e.g. car - is present in the image according to its visual content. Today, with the massive use of smartphones and social networks, images are ubiquitous in our daily lives. To process and exploit this mass of data, it is important to have recognition systems, to analyze and interpret the visual content of the images. We propose in this manuscript to learn localized representations with weakly supervised learning methods. In the image classification setting, this problem can be seen as a problem of pooling on regions. From the Multiple Instance Learning (MIL) formalism, we proposed SyMIL, which is a symmetric model for the binary classification of bags. SyMIL uses a pooling function, which seeks discriminative instances for each category. Then, we generalized SyMIL to structured prediction problems, introducing MANTRA. MANTRA seeks discriminative regions for the class, but also regions indicating the absence of the class (negative evidence). Thereafter, we integrated the negative evidence model into a deep architecture. We also propose an extension of the pooling function to several regions, to be more robust. In the last section, we proposed a new architecture that learns several modalities for each class class - to have better prediction. We also proposed a unified model for pooling, and an experimental comparison on 6 datasets.
Defence : 09/20/2017
Jury members :
PEREZ Patrick (Technicolor) [Rapporteur]
RAKOTOMAMONJY Alain (INSA DE ROUEN - LITIS) [Rapporteur]
BACH Francis (INRIA - Ecole Normale Superieure)
CORD Matthieu (UPMC - LIP6)
SCHMID Cordelia (INRIA - THOTH)
SERFATY Véronique (DGA)
THOME Nicolas (CNAM - CEDRIC)
2013-2019 Publications
-
2019
- Th. Durand, N. Thome, M. Cord : “Exploiting Negative Evidence for Deep Latent Structured Models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41 (2), pp. 337-351, (Institute of Electrical and Electronics Engineers) (2019)
-
2018
- Th. Durand, N. Thome, M. Cord : “SyMIL: MinMax Latent SVM for Weakly Labeled Data”, IEEE Transactions on Neural Networks and Learning Systems, vol. 29 (12), pp. 6099-6112, (IEEE) (2018)
-
2017
- Th. Durand : “Apprentissage faiblement supervisé pour la reconnaissance visuelle”, thesis, phd defence 09/20/2017, supervision Cord, Matthieu, co-supervision : Thome, Nicolas (2017)
- Th. Durand, T. Mordan, N. Thome, M. Cord : “WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation”, IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, United States, pp. 5957-5966 (2017)
-
2016
- Th. Durand, N. Thome, M. Cord : “WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks”, 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, United States (2016)
-
2015
- Th. Durand, N. Thome, M. Cord : “MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking”, IEEE International Conference on Computer Vision (ICCV15), Santiago, Chile (2015)
-
2014
- Th. Durand, N. Thome, M. Cord, D. Picard : “Incremental learning of latent structural SVM for weakly supervised image classification”, IEEE International Conference on Image Processing, Paris, France, pp. 4246-4250, (IEEE) (2014)
- Th. Durand, D. Picard, N. Thome, M. Cord : “SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING”, IEEE International Conference on Image Processing, Paris, France, (Institute of Electrical and Electronics Engineers) (2014)
-
2013
- Th. Durand, N. Thome, M. Cord, S. Avila : “Image classification using object detectors”, ICIP 2013 : IEEE International Conference on Image Processing, Melbourne, Australia, pp. 4340-4344 (2013)