Remote Sensing Image Scene Classification via Self-Supervised Learning and Knowledge Distillation
The main challenges of remote sensing image scene classification are extracting discriminative features and making full use of the training data. The current mainstream deep learning methods usually only use the hard labels of the samples, ignoring the potential soft labels and natural labels. Self-...
Main Authors: | Yibo Zhao, Jianjun Liu, Jinlong Yang, Zebin Wu |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/19/4813 |
Similar Items
-
RS-SSKD: Self-Supervision Equipped with Knowledge Distillation for Few-Shot Remote Sensing Scene Classification
by: Pei Zhang, et al.
Published: (2021-02-01) -
Collaborative Consistent Knowledge Distillation Framework for Remote Sensing Image Scene Classification Network
by: Shiyi Xing, et al.
Published: (2022-10-01) -
Two-Stage Fusion-Based Audiovisual Remote Sensing Scene Classification
by: Yaming Wang, et al.
Published: (2023-10-01) -
Remote Sensing Image Scene Classification with Noisy Label Distillation
by: Rui Zhang, et al.
Published: (2020-07-01) -
An Inverted Residual Cross Head Knowledge Distillation Network for Remote Sensing Scene Image Classification
by: Cuiping Shi, et al.
Published: (2025-01-01)