• Amélie Royer, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Mosseri, Forrester Cole, Kevin Murphy. "XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings", Domain Adaptation for Visual Understanding Workshop at ICML/IJCAI/EJCAI 2018

    [Bibtex] [Abstract] [PDF] [Slides]

  • Amélie Royer*, Alexander Kolesnikov*, Christoph Lampert. "Probabilistic Image Colorization", British Machine Vision Conference, 2017.

    (∗) equal contribution

    [Bibtex] [Abstract] [PDF]

  • Amélie Royer, Guillaume Gravier, Vincent Claveau. "Audio word similarity for clustering with zero resources based on iterative HMM classification", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016.

    [Bibtex] [Abstract] [PDF] [Poster]

  • Amélie Royer, Christoph H. Lampert. "Classifier Adaptation at Prediction Time", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.

    [Bibtex] [Abstract] [PDF]

Technical Reports

  • Amélie Royer, Guillaume Gravier, Vincent Claveau, Teddy Furon. "Similarity by diverting supervised machine learning — Application to knowledge discovery in multimedia content", Research Report Inria Rennes Bretagne Atlantique, 2015.

    [Bibtex] [Abstract] [PDF]

  • () Antoine Chatalic, Siargey Kachanovich, Amélie Royer, Lucas Seguinot, Baptiste Tessiau, Alix Trieu. "Aide à la conception et vérification de spécifications formelles de protocoles cryptographiques en ProVérif", Masters Research Project, 2014.

    [Bibtex] [Abstract] [PDF]


Probabilistic Image Colorization (PIC)

Summary Download

Tensorflow implementation for Probabilistic Image Colorization - generating diverse and vibrant colorization using auto-regressive generative networks - on the CIFAR and ImageNet datasets.

  • PIC repository
    • Source code written for Python 2.6+ and 3+ and Tensorflow
    • Pretrained models available for CIFAR and ImageNet
    • MIT license

Similarity by Iterative Classification (SIC)

Summary Download

Implementation of SIC (Similarity by Iterative Classification), an unsupervised machine learning technique to estimate a similarity measures from repeated classification iterations on the data. See the following technical report for more details about the method, implementation and datasets used:


Classifier Adaptation at Prediction Time

Summary Download

Python implementation of an online classifier adaptation scheme at prediction time. The archive contains the implementation for running and evaluation the classifier adaptations, as well as for generating "realistic sequences" of object categories as described in the original work.

    • Source code written for Python 2.6+
    • Instructions and Dependencies in README file + Sphinx Documentation (Doc/ directory)
    • GNU GPL v2.0 license
    • Example of realistic query sequences precomputed for the ILSVRC2010 and ILSVRC2012 datasets (Data/ directory)