Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learning

no code implementations • 23 Nov 2023 • Marc Schachtsiek, Simone Rossi, Thomas Hannagan

The more balanced labels increase minority class performance, which in turn allows the model to outperform the previous baseline by 0. 6, 1. 7, and 2. 4 mIoU for budgets of 5%, 10%, and 20%, respectively.

Active Learning Semantic Segmentation

Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU

1 code implementation • 13 Jun 2022 • Hugo Tessier, Vincent Gripon, Mathieu Léonardon, Matthieu Arzel, David Bertrand, Thomas Hannagan

Deep neural networks are the state of the art in many computer vision tasks.

Autonomous Driving Semantic Segmentation

Leveraging Structured Pruning of Convolutional Neural Networks

1 code implementation • 13 Jun 2022 • Hugo Tessier, Vincent Gripon, Mathieu Léonardon, Matthieu Arzel, David Bertrand, Thomas Hannagan

Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many computer vision tasks.

Rethinking Weight Decay For Efficient Neural Network Pruning

1 code implementation • 20 Nov 2020 • Hugo Tessier, Vincent Gripon, Mathieu Léonardon, Matthieu Arzel, Thomas Hannagan, David Bertrand

Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks.

Efficient Neural Network Network Pruning