Search Results for author:
Found 26 papers, 10 papers with code
Un jeu de données pour répondre à des questions visuelles à propos d’entités nommées en utilisant des bases de connaissances (ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities)
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).
xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion
Additionally, we propose a late-fusion technique tailored to our pipeline that further enhances performance when both modalities are available at inference.
Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
Face recognition and verification are two computer vision tasks whose performances have advanced with the introduction of deep representations.
Automatic Die Studies for Ancient Numismatics
We validate the approach on two corpora of Greek coins, propose an automatic implementation and evaluation of previous baselines, and show that our approach significantly outperforms them.
ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only
We further demonstrate the effectiveness and robustness of our method by being the first to experiment on the more challenging nuScenes dataset.
Toward Fairer Face Recognition Datasets
We promote fairness by introducing a demographic attributes balancing mechanism in generated training datasets.
Smooth Pseudo-Labeling
Semi-Supervised Learning (SSL) seeks to leverage large amounts of non-annotated data along with the smallest amount possible of annotated data in order to achieve the same level of performance as if all data were annotated.
Detection of Thermal Events by Semi-Supervised Learning for Tokamak First Wall Safety
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.
Semantic Generative Augmentations for Few-Shot Counting
This requires to generate images that correspond to a given input number of objects.
Ranked #7 on
Object Counting
on FSC147
(using extra training data)
TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation
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.
Wasserstein Loss for Semantic Editing in the Latent Space of GANs
The latent space of GANs contains rich semantics reflecting the training data.
Self-Improving SLAM in Dynamic Environments: Learning When to Mask
Thus, we propose a novel SLAM that learns when masking objects improves its performance in dynamic scenarios.
ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities
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.
Learning Semantic Ambiguities for Zero-Shot Learning
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.
Multi-Attribute Balanced Sampling for Disentangled GAN Controls
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.
Zero-shot Learning with Deep Neural Networks for Object Recognition
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.
AVAE: Adversarial Variational Auto Encoder
Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN).
Learning to Segment Dynamic Objects using SLAM Outliers
Our dataset includes consensus inversions, i. e., situations where the SLAM uses more features on dynamic objects that on the static background.
Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning
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.
Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning
When the number of classes is large, classes are usually represented by semantic class prototypes learned automatically from unannotated text collections.
Controlling generative models with continuous factors of variations
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.
Learning Finer-class Networks for Universal Representations
This raises the question of how well the original representation is "universal", that is to say directly adapted to many different target-tasks.
From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process
Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes.
Learning More Universal Representations for Transfer-Learning
We also propose a unified framework of the methods based on the diversifying of the training problem.
On Deep Representation Learning from Noisy Web Images
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.
Scalable domain adaptation of convolutional neural networks
Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems.
