Výsledky vyhledávání

Report

Image Compression using only Attention based Neural Networks

Autor: Luka, Natacha, Negrel, Romain, Picard, David

In recent research, Learned Image Compression has gained prominence for its capacity to outperform traditional handcrafted pipelines, especially at low bit-rates. While existing methods incorporate convolutional priors with occasional attention block

Externí odkaz: http://arxiv.org/abs/2310.11265

Zobrazit plný text záznamu

Report

Domain-Aware Augmentations for Unsupervised Online General Continual Learning

Autor: Michel, Nicolas, Negrel, Romain, Chierchia, Giovanni, Bercher, Jean-François

Continual Learning has been challenging, especially when dealing with unsupervised scenarios such as Unsupervised Online General Continual Learning (UOGCL), where the learning agent has no prior knowledge of class boundaries or task change informatio

Externí odkaz: http://arxiv.org/abs/2309.06896

Zobrazit plný text záznamu

Report

New metrics for analyzing continual learners

Autor: Michel, Nicolas, Chierchia, Giovanni, Negrel, Romain, Bercher, Jean-François, Yamasaki, Toshihiko

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of data wher

Externí odkaz: http://arxiv.org/abs/2309.00462

Zobrazit plný text záznamu

Report

Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning

Autor: Michel, Nicolas, Chierchia, Giovanni, Negrel, Romain, Bercher, Jean-François

We use the maximum a posteriori estimation principle for learning representations distributed on the unit sphere. We propose to use the angular Gaussian distribution, which corresponds to a Gaussian projected on the unit-sphere and derive the associa

Externí odkaz: http://arxiv.org/abs/2306.03364

Zobrazit plný text záznamu

Report

Contrastive Learning for Online Semi-Supervised General Continual Learning

Autor: Michel, Nicolas, Negrel, Romain, Chierchia, Giovanni, Bercher, Jean-François

We study Online Continual Learning with missing labels and propose SemiCon, a new contrastive loss designed for partly labeled data. We demonstrate its efficiency by devising a memory-based method trained on an unlabeled data stream, where every data

Externí odkaz: http://arxiv.org/abs/2207.05615

Zobrazit plný text záznamu