no code implementations • JEP/TALN/RECITAL 2022 • Paul Lerner, Olivier Ferret, Camille Guinaudeau, Hervé Le Borgne, Romaric Besançon, Jose Moreno, Jesús Lovón-Melgarejo
Dans le contexte général des traitements multimodaux, nous nous intéressons à la tâche de réponse à des questions visuelles à propos d’entités nommées en utilisant des bases de connaissances (KVQAE).
no code implementations • 19 Jan 2024 • Christian Staron, Hervé Le Borgne, Raphaël Mitteau, Erwan Grelier, Nicolas Allezard
Semi-supervised learning (SSL) is a possible solution to being able to train deep learning models with a small amount of labelled data and a large amount of unlabelled data.
1 code implementation • 26 Oct 2023 • Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne
This requires to generate images that correspond to a given input number of objects.
Ranked #4 on Object Counting on FSC147 (using extra training data)
1 code implementation • 11 Jul 2023 • Paul Grimal, Hervé Le Borgne, Olivier Ferret, Julien Tourille
While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images based on a prompt, to consider additional aspects such as to which extent the generated image matches the important content of the prompt.
no code implementations • 22 Mar 2023 • Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne
The latent space of GANs contains rich semantics reflecting the training data.
1 code implementation • 15 Oct 2022 • Adrian Bojko, Romain Dupont, Mohamed Tamaazousti, Hervé Le Borgne
Thus, we propose a novel SLAM that learns when masking objects improves its performance in dynamic scenarios.
1 code implementation • SIGIR 2022 • Paul Lerner, Olivier Ferret, Camille Guinaudeau, Hervé Le Borgne, Romaric Besançon, Jose G Moreno, Jesús Lovón Melgarejo
To benchmark this task, called KVQAE (Knowledge-based Visual Question Answering about named Entities), we provide ViQuAE, a dataset of 3. 7K questions paired with images.
1 code implementation • 5 Jan 2022 • Celina Hanouti, Hervé Le Borgne
State of the art approaches rely on generative models that synthesize visual features from the prototype of a class, such that a classifier can then be learned in a supervised manner.
1 code implementation • 28 Oct 2021 • Perla Doubinsky, Nicolas Audebert, Michel Crucianu, Hervé Le Borgne
We propose to address disentanglement by subsampling the generated data to remove over-represented co-occuring attributes thus balancing the semantics of the dataset before training the classifiers.
no code implementations • 5 Feb 2021 • Yannick Le Cacheux, Hervé Le Borgne, Michel Crucianu
The general approach is to learn a mapping from visual data to semantic prototypes, then use it at inference to classify visual samples from the class prototypes only.
no code implementations • 21 Dec 2020 • Antoine Plumerault, Hervé Le Borgne, Céline Hudelot
Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN).
no code implementations • 12 Nov 2020 • Adrian Bojko, Romain Dupont, Mohamed Tamaazousti, Hervé Le Borgne
Our dataset includes consensus inversions, i. e., situations where the SLAM uses more features on dynamic objects that on the static background.
no code implementations • 6 Oct 2020 • Yannick Le Cacheux, Hervé Le Borgne, Michel Crucianu
Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic representations.
no code implementations • 6 Aug 2020 • Yannick Le Cacheux, Adrian Popescu, Hervé Le Borgne
When the number of classes is large, classes are usually represented by semantic class prototypes learned automatically from unannotated text collections.
1 code implementation • ICLR 2020 • Antoine Plumerault, Hervé Le Borgne, Céline Hudelot
Recent deep generative models are able to provide photo-realistic images as well as visual or textual content embeddings useful to address various tasks of computer vision and natural language processing.
no code implementations • 4 Oct 2018 • Julien Girard, Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot
This raises the question of how well the original representation is "universal", that is to say directly adapted to many different target-tasks.
no code implementations • 26 Sep 2018 • Yannick Le Cacheux, Hervé Le Borgne, Michel Crucianu
Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes.
1 code implementation • 27 Dec 2017 • Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot, Mohamed El Amine Seddik, Mohamed Tamaazousti
We also propose a unified framework of the methods based on the diversifying of the training problem.
no code implementations • 15 Dec 2015 • Phong D. Vo, Alexandru Ginsca, Hervé Le Borgne, Adrian Popescu
The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks.
no code implementations • 7 Dec 2015 • Adrian Popescu, Etienne Gadeski, Hervé Le Borgne
Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems.