.png){kind=icon}
返回
Variational Self-Distillation for Remote Sensing Scene Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2022.3194549.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Supported by deep learning techniques, remote sensing scene classification, a fundamental task in remote image analysis, has recently obtained remarkable progress. However, due to the severe uncertainty and perturbation within an image, it is still a challenging task and remains many unsolved problems. In this article, we note that regular one-hot labels cannot precisely describe remote sensing images, and they fail to provide enough information for supervision and limiting the discriminative feature learning of the network. To solve this problem, we propose a variational self-distillation network (VSDNet), in which the class entanglement information from the prediction vector acts as the supplement to the category information. Then, the exploited information is hierarchically distilled from the deep layers into the shallow parts via a variational knowledge transfer (VKT) module. Notably, the VKT module performs knowledge distillation in a probabilistic way through variational estimation, which enables end-to-end optimization for mutual information and promotes robustness to uncertainty within the image. Extensive experiments on four challenging remote sensing datasets demonstrate that, with a negligible parameter increase, the proposed VSDNet brings a significant performance improvement over different backbone networks and delivers state-of-the-art results.
Keyword:
Remote sensing
Training
Representation learning
Uncertainty
Perturbation methods
Knowledge transfer
Computational modeling
Class entanglement information
hierarchical knowledge transfer
remote sensing scene classification
self-distillation
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
分享收藏Crystalline‐State Reaction with Allosteric Effect in Spin‐Crossover, Interpenetrated Networks with Magnetic and Optical Bistability具有磁和光学双稳态的自旋交叉，互穿网络中具有变构效应的晶态反应
PREAI
分享收藏High-Resolution Remote Sensing Image Scene Classification via Key Filter Bank Based on Convolutional Neural Network基于关键滤波器组的卷积神经网络高分辨率遥感影像场景分类
PREAI
分享收藏A Feature Aggregation Convolutional Neural Network for Remote Sensing Scene Classification用于遥感场景分类的特征聚合卷积神经网络
PREAI
分享收藏
查看更多内容