3 papers
cs.CV2022
Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information
Ahmed Ben Saad, Kristina Prokopetc, Josselin Kherroubi +3
Self-supervised representation learning based on Contrastive Learning (CL) has been the subject of much attention in recent years. This is due to the excellent results obtained on…
cs.CV2022
Can neural networks extrapolate? Discussion of a theorem by Pedro Domingos
Adrien Courtois, Jean-Michel Morel, Pablo Arias
Neural networks trained on large datasets by minimizing a loss have become the state-of-the-art approach for resolving data science problems, particularly in computer vision, image…
cs.CV2022
Investigating Neural Architectures by Synthetic Dataset Design
Adrien Courtois, Jean-Michel Morel, Pablo Arias
Recent years have seen the emergence of many new neural network structures (architectures and layers). To solve a given task, a network requires a certain set of abilities reflecte…