3 papers
cs.LG2021
DAEMA: Denoising Autoencoder with Mask Attention
Simon Tihon, Muhammad Usama Javaid, Damien Fourure +2
Missing data is a recurrent and challenging problem, especially when using machine learning algorithms for real-world applications. For this reason, missing data imputation has bec…
cs.CV2021
A Framework using Contrastive Learning for Classification with Noisy Labels
Madalina Ciortan, Romain Dupuis, Thomas Peel
We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies such as pseudo-labeling,…
cs.CL2019
STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings
Léo Bouscarrat, Antoine Bonnefoy, Thomas Peel +1
This paper introduces STRASS: Summarization by TRAnsformation Selection and Scoring. It is an extractive text summarization method which leverages the semantic information in exist…