80 citations · 104 across the 17 of their papers we have counts for
20 papers
The Deleuzian Representation Hypothesis
Clément Cornet, Romaric Besançon, Hervé Le Borgne
We propose an alternative to sparse autoencoders (SAEs) as a simple and effective unsupervised method for extracting interpretable concepts from neural networks. The core idea is t…
Reliable and Reproducible Demographic Inference for Fairness in Face Analysis
Alexandre Fournier-Montgieux, Hervé Le Borgne, Adrian Popescu +1
Fairness evaluation in face analysis systems (FAS) typically depends on automatic demographic attribute inference (DAI), which itself relies on predefined demographic segmentation.…
CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
Frédéric LIN, Biruk Abere Ambaw, Adrian Popescu +3
AI systems must adapt to evolving visual environments, especially in domains where object appearances change over time. We introduce Car Models in Time (CaMiT), a fine-grained data…
MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection
Saad Lahlali, Alexandre Fournier Montgieux, Nicolas Granger +2
Annotating 3D data remains a costly bottleneck for 3D object detection, motivating the development of weakly supervised annotation methods that rely on more accessible 2D box annot…
SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation
Paul Grimal, Michaël Soumm, Hervé Le Borgne +2
State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts, leading to missing critical elements or uninten…
Explaining How Visual, Textual and Multimodal Encoders Share Concepts
Clément Cornet, Romaric Besançon, Hervé Le Borgne
Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different mode…
Text-to-Image Alignment in Denoising-Based Models through Step Selection
Paul Grimal, Hervé Le Borgne, Olivier Ferret
Visual generative AI models often encounter challenges related to text-image alignment and reasoning limitations. This paper presents a novel method for selectively enhancing the s…
Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
Alexandre Fournier-Montgieux, Michael Soumm, Adrian Popescu +2
Face recognition and verification are two computer vision tasks whose performances have advanced with the introduction of deep representations. However, ethical, legal, and technic…
Semantic Generative Augmentations for Few-Shot Counting
Perla Doubinsky, Nicolas Audebert, Michel Crucianu +1
With the availability of powerful text-to-image diffusion models, recent works have explored the use of synthetic data to improve image classification performances. These works sho…
TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation
Paul Grimal, Hervé Le Borgne, Olivier Ferret +1
The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is cr…
Wasserstein Loss for Semantic Editing in the Latent Space of GANs
Perla Doubinsky, Nicolas Audebert, Michel Crucianu +1
The latent space of GANs contains rich semantics reflecting the training data. Different methods propose to learn edits in latent space corresponding to semantic attributes, thus a…
Self-Improving SLAM in Dynamic Environments: Learning When to Mask
Adrian Bojko, Romain Dupont, Mohamed Tamaazousti +1
Visual SLAM - Simultaneous Localization and Mapping - in dynamic environments typically relies on identifying and masking image features on moving objects to prevent them from nega…
Multi-Attribute Balanced Sampling for Disentangled GAN Controls
Perla Doubinsky, Nicolas Audebert, Michel Crucianu +1
Various controls over the generated data can be extracted from the latent space of a pre-trained GAN, as it implicitly encodes the semantics of the training data. The discovered co…
AVAE: Adversarial Variational Auto Encoder
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). GANs can produce realistic image…
Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning
Yannick Le Cacheux, Adrian Popescu, Hervé Le Borgne
Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual training data for a part of the classes from a dataset. When the number of classes is larg…
Controlling generative models with continuous factors of variations
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 natu…
Learning Finer-class Networks for Universal Representations
Julien Girard, Youssef Tamaazousti, Hervé Le Borgne +1
Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to d…
From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process
Yannick Le Cacheux, Hervé Le Borgne, Michel Crucianu
Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes. It relies on additional semantic knowledge for which a mapping can be learned with training…
Scalable domain adaptation of convolutional neural networks
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. Besides important theoretical and practical advances in t…
On Deep Representation Learning from Noisy Web Images
Phong D. Vo, Alexandru Ginsca, Hervé Le Borgne +1
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 classificatio…