output
20022026
most citedPaying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer

1.6k citations

Showing 2023 · cs.LGShow all

8 papers · 2 filters

cs.LG2023

Improving Plasticity in Online Continual Learning via Collaborative Learning

Maorong Wang, Nicolas Michel, Ling Xiao +1

Online Continual Learning (CL) solves the problem of learning the ever-emerging new classification tasks from a continuous data stream. Unlike its offline counterpart, in online CL…

cs.LG2023

Class Uncertainty: A Measure to Mitigate Class Imbalance

Z. S. Baltaci, K. Oksuz, S. Kuzucu +5

Class-wise characteristics of training examples affect the performance of deep classifiers. A well-studied example is when the number of training examples of classes follows a long…

cs.LG2023★ 1 cited

SWMLP: Shared Weight Multilayer Perceptron for Car Trajectory Speed Prediction using Road Topographical Features

Sarah Almeida Carneiro, Giovanni Chierchia, Jean Charléty +2

Although traffic is one of the massively collected data, it is often only available for specific regions. One concern is that, although there are studies that give good results for…

cs.LG2023

Exact and general decoupled solutions of the LMC Multitask Gaussian Process model

Olivier Truffinet, Karim Ammar, Jean-Philippe Argaud +1

The Linear Model of Co-regionalization (LMC) is a very general multitask gaussian process model for regression or classification. While its expressiveness and conceptual simplicity…

cs.LG2023

An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning

Grégoire Petit, Michael Soumm, Eva Feillet +4

Class-Incremental Learning (CIL) aims to build classification models from data streams. At each step of the CIL process, new classes must be integrated into the model. Due to catas…

cs.LG2023★ 1 cited

Domain-Aware Augmentations for Unsupervised Online General Continual Learning

Nicolas Michel, Romain Negrel, Giovanni Chierchia +1

Continual Learning has been challenging, especially when dealing with unsupervised scenarios such as Unsupervised Online General Continual Learning (UOGCL), where the learning agen…