1 citations · 1 across the 3 of their papers we have counts for
4 papers
Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document
Adnan Ben Mansour, Ayoub Karine, David Naccache
Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Char…
Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
Aymene Mohammed Bouayed, Samuel Deslauriers-Gauthier, Adrian Iaccovelli +1
Variational Autoencoders (VAEs) with global priors trained under an imbalanced empirical class distribution can lead to underrepresentation of tail classes in the latent space. Whi…
FedPID: An Aggregation Method for Federated Learning
Leon Mächler, Gustav Grimberg, Ivan Ezhov +4
This paper presents FedPID, our submission to the Federated Tumor Segmentation Challenge 2024 (FETS24). Inspired by FedCostWAvg and FedPIDAvg, our winning contributions to FETS21 a…
CNN Explainability with Multivector Tucker Saliency Maps for Self-Supervised Models
Aymene Mohammed Bouayed, Samuel Deslauriers-Gauthier, Adrian Iaccovelli +1
Interpreting the decisions of Convolutional Neural Networks (CNNs) is essential for understanding their behavior, yet explainability remains a significant challenge, particularly f…