PLOP: Learning without Forgetting for Continual Semantic Segmentation

2020-11-23 · CVPR 2021 1 · Arthur Douillard, Yifu Chen, Arnaud Dapogny, Matthieu Cord

Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an emerging trend that consists in updating an old model by sequentially adding new classes. However, continual learning methods are usually prone to catastrophic forgetting. This issue is further aggravated in CSS where, at each step, old classes from previous iterations are collapsed into the background. In this paper, we propose Local POD, a multi-scale pooling distillation scheme that preserves long- and short-range spatial relationships at feature level. Furthermore, we design an entropy-based pseudo-labelling of the background w.r.t. classes predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes. Our approach, called PLOP, significantly outperforms state-of-the-art methods in existing CSS scenarios, as well as in newly proposed challenging benchmarks.

📄 PDF Abstract BibTeX arXiv:2011.11390

Code (2)

arthurdouillard/CVPR2021_PLOP 공식 구현 pytorch

mostafaelaraby/bacs-continual-semantic-segmentation pytorch

Tasks

Class Incremental Learning Continual Learning Continual Semantic Segmentation Disjoint 10-1 Disjoint 15-1 Disjoint 15-5Domain 1-1Domain 11-1Domain 11-5Overlapped 100-10 Overlapped 100-5 Overlapped 100-50 Overlapped 10-1 Overlapped 15-1 Overlapped 15-5Overlapped 19-1Overlapped 50-50 Segmentation Semantic Segmentation

Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation

2021-06-29 · Arthur Douillard, Yifu Chen, Arnaud Dapogny, Matthieu Cord

Class Incremental Learning Continual Learning Continual Semantic Segmentation Overlapped 10-1+4

ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning

2024-03-29 · CVPR 2024 1 · Beomyoung Kim, Joonsang Yu, Sung Ju Hwang

Panoptic segmentation, combining semantic and instance segmentation, stands as a cutting-edge computer vision task. Despite recent progress with deep learning models, the dynamic nature of real-world applications necessi…

Continual Learning Continual Panoptic Segmentation Instance Segmentation Knowledge Distillation+4

kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies

2024-04-15 · Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan 외

Continual segmentation has not yet tackled the challenge of improving open-vocabulary segmentation models with training data for accurate segmentation across large, continually expanding vocabularies. We discover that tr…

Panoptic Segmentation Retrieval Segmentation Zero Shot Segmentation

Representation Compensation Networks for Continual Semantic Segmentation

2022-03-10 · CVPR 2022 1 · Chang-Bin Zhang, Jia-Wen Xiao, Xialei Liu, Ying-Cong Chen 외

In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-pa…

Class Incremental Learning Continual Learning Continual Semantic Segmentation Disjoint 10-1+15

Decoupling Continual Semantic Segmentation

2025-08-07 · Yifu Guo, Yuquan Lu, Wentao Zhang, Zishan Xu 외 arxiv

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, ex…

Continual Semantic Segmentation Continual Learning