Incremental Learning in Semantic Segmentation from Image Labels

2021-12-03 · CVPR 2022 1 · Fabio Cermelli, Dario Fontanel, Antonio Tavera, Marco Ciccone, Barbara Caputo

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and time-consuming. This paper proposes a novel framework for Weakly Incremental Learning for Semantic Segmentation, that aims at learning to segment new classes from cheap and largely available image-level labels. As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally. We cope with the inherent noise in the process by using soft-labels generated by the auxiliary classifier. We demonstrate the effectiveness of our approach on the Pascal VOC and COCO datasets, outperforming offline weakly-supervised methods and obtaining results comparable with incremental learning methods with full supervision. Code can be found at https://github.com/fcdl94/WILSON.

📄 PDF Abstract BibTeX arXiv:2112.01882

Code (1)

fcdl94/wilson 공식 구현 pytorch

Tasks

Incremental Learning Segmentation Semantic Segmentation

Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision

2023-01-01 · ICCV 2023 1 · Yu-Hsing Hsieh, Guan-Sheng Chen, Shun-Xian Cai, Ting-Yun Wei 외

Instance segmentation requires labor-intensive manual labeling of the contours of complex objects in images for training. The labels can also be provided incrementally in practice to balance the human labor in differ…

Continual Learning Incremental Learning Instance Segmentation Segmentation+4

Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation

2023-02-28 · CVPR 2023 1 · Chaohui Yu, Qiang Zhou, Jingliang Li, Jianlong Yuan 외

Modern incremental learning for semantic segmentation methods usually learn new categories based on dense annotations. Although achieve promising results, pixel-by-pixel labeling is costly and time-consuming. Weakly incr…

Incremental Learning Segmentation Semantic Segmentation

Completely Weakly Supervised Class-Incremental Learning for Semantic Segmentation

2025-05-16 · David Minkwan Kim, Soeun Lee, Byeongkeun Kang

This work addresses the task of completely weakly supervised class-incremental learning for semantic segmentation to learn segmentation for both base and additional novel classes using only image-level labels. While clas…

class-incremental learning Class Incremental Learning Class-Incremental Semantic Segmentation Data Augmentation+3

Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels

2020-05-12 · Marvin Klingner, Andreas Bär, Philipp Donn, Tim Fingscheidt

While neural networks trained for semantic segmentation are essential for perception in autonomous driving, most current algorithms assume a fixed number of classes, presenting a major limitation when developing new auto…

Autonomous Driving class-incremental learning Class Incremental Learning Incremental Learning+2

Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation

2021-04-02 · Zilong Huang, Wentian Hao, Xinggang Wang, Mingyuan Tao 외

Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial trainin…

Class-Incremental Semantic Segmentation Diversity Incremental Learning Segmentation+1