Class incremental learning of remote sensing images based on class similarity distillation.

ABSTRACT: When a well-trained model learns a new class, the data distribution differences between the new and old classes inevitably cause catastrophic forgetting in order to perform better in the new class. This behavior differs from human learning. In this article, we propose a class incremental object detection method for remote sensing images to address the problem of catastrophic forgetting caused by distribution differences among different classes. First, we introduce a class similarity distillation (CSD) loss based on the similarity between new and old class prototypes, ensuring the model's plasticity to learn new classes and stability to detect old classes. Second, to better extract class similarity features, we propose a global similarity distillation (GSD) loss that maximizes the mutual in

SUBMITTER: Shen M 

PROVIDER: S-EPMC10557500 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature