Endpoints Weight Fusion for Class Incremental Semantic Segmentation
By Jianqiang Xiao, Chang-Bin Zhang, Jiekang Feng, Xialei Liu, Joost van de Weijer, Mingg-Ming Cheng. 2023
77 citations recorded by the source corpus.
Class incremental semantic segmentation (CISS) focuses on alleviating catastrophic forgetting to improve discrimination. Previous work mainly exploits regularization (e.g., knowledge distillation) to maintain previous knowledge in the current model. However, distillation alone often yields limited gain to the model since only the representations of old and new models are restricted to be consistent. In this paper, we propose a simple yet effective method to obtain a model with a strong memory of old knowledge, named Endpoints Weight Fusion (EWF). In our method, the model containing old knowledge is fused with the model retaining new knowledge in a dynamic fusion manner, strengthening the memory of old classes in ever changing distributions. In addition, we analyze the relationship between our fusion strategy and a popular moving average technique EMA, which reveals why our method is more suitable for class-incremental learning. To facilitate parameter fusion with closer distance in the parameter space, we use distillation to enhance the optimization process. Furthermore, we conduct experiments on two widely used datasets, achieving state-of-the-art performance.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
In Radiology, Nuclear Medicine and Imaging
Citations in the corpus
- Recent Advances of Continual Learning in Computer Vision: An Overview (2021, neutral): “Xiao et al. [71] incorporated the idea of knowledge distillation together with the idea of model ensemble.”
- Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation (2024, background): “MiB [4] proposes a novel unbiased function to model background shift.”
- Continual Segmentation with Disentangled Objectness Learning and Class Recognition (2024, unknown): “While the research focus of continual learning is on classification [1, 6, 11, 22, 25, 38, 41, 50, 58], continual segmentation started to thrive recently [3, 5, 7, 12, 32, 36, 40, 51, 57, 60, 61, 65].”
- Class-Incremental Learning: A Survey (2023, background): “EWF [281] utilizes model fusion among different stage backbones to strike a balance between old and new knowledge.”