Class incremental learning of remote sensing images based on class similarity distillation
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 dete...
Main Authors: | Mingge Shen, Dehu Chen, Silan Hu, Gang Xu |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2023-09-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-1583.pdf |
Similar Items
-
A Class-Incremental Detection Method of Remote Sensing Images Based on Selective Distillation
by: Hang Ruan, et al.
Published: (2022-10-01) -
Class-Prompting Transformer for Incremental Semantic Segmentation
by: Zichen Song, et al.
Published: (2023-01-01) -
Contrast metric enhancement based on memory extraction for online class-incremental learning in image classification
by: WANG Honghui, YIN Jinyong, YANG Jian
Published: (2024-02-01) -
Meta-Learning Based Tasks Similarity Representation for Cross Domain Lifelong Learning
by: Mingge Shen, et al.
Published: (2023-01-01) -
A Class-Incremental Learning Method Based on Preserving the Learned Feature Space for EEG-Based Emotion Recognition
by: Magdiel Jiménez-Guarneros, et al.
Published: (2022-02-01)