activity
20242026
collaborators

11 papers

cs.CV2026

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…

cs.LG2025

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…

cs.CV2025

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.…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…