.png){kind=icon}
返回
MITformer: A Multiinstance Vision Transformer for Remote Sensing Scene Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2022.3176499.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The latest vision transformer (ViT) has stronger contextual feature representation capability than the existing convolutional neural networks and thus has the potential to depict the remote sensing scenes, which usually have more complicated object distribution and spatial arrangement than ground image scenes. However, recent researches reflect that while ViT learns global features, it also ignores the key local features, which poses a bottleneck for understanding remote sensing scenes. In this letter, we tackle this challenge by proposing a novel multiinstance vision transformer (MITformer). Its originality mainly lies in the classic multiple instance learning (MIL) formulation, where each image patch embedded in ViT is regarded as an instance and each image is regarded as a bag. The benefit of designing ViT under MIL formulation is straightforward, as it helps highlight the feature response of key local regions of remote sensing scenes. Moreover, to enhance the feature propagation of local features, attention-based multilayer perceptron (AMLP) head is embedded at the end of each encoder unit. Finally, to minimize the potential semantic prediction differences between the classic ViT and our MIL head, a semantic consistency loss is designed. Experiments on three remote sensing scene classification benchmarks show that our proposed MITformer outperforms the existing state-of-the-art methods and validate the effectiveness of each component in our MITformer.
Keyword:
Remote sensing
Transformers
Probability distribution
Semantics
Image analysis
Head
Sensors
Feature propagation
multiinstance learning
remote sensing image
scene classification
vision transformer (ViT)
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
引用论文
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏History of tropospheric ozone for the San Bernardino Mountains of Southern California, 1963–1999
PREAI
分享收藏
Progressive Contextual Instance Refinement for Weakly Supervised Object Detection in Remote Sensing Images用于遥感图像中弱监督目标检测的渐进式上下文实例细化
PREAI
分享收藏分享收藏RADC-Net: A residual attention based convolution network for aerial scene classification.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容