17 citations · 29 across the 4 of their papers we have counts for
6 papers · 1 filter
CoMFormer: Continual Learning in Semantic and Panoptic Segmentation
Fabio Cermelli, Matthieu Cord, Arthur Douillard
Continual learning for segmentation has recently seen increasing interest. However, all previous works focus on narrow semantic segmentation and disregard panoptic segmentation, an…
Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation
Antoine Saporta, Arthur Douillard, Tuan-Hung Vu +2
Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain. Beyond the traditional…
Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
Arthur Douillard, Yifu Chen, Arnaud Dapogny +1
Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power.…
PLOP: Learning without Forgetting for Continual Semantic Segmentation
Arthur Douillard, Yifu Chen, Arnaud Dapogny +1
Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power.…
Insights from the Future for Continual Learning
Arthur Douillard, Eduardo Valle, Charles Ollion +2
Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting. In this…
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning
Arthur Douillard, Matthieu Cord, Charles Ollion +2
Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learn…