Remote sensing scene classification is still a challenging task in remote sensing applications. How to effectively extract features from a dataset with limited scale is crucial for improvement of scene classification. Recently, convolutional neural network (CNN) performs impressively in different fields of computer vision and has been used for remote sensing. However, most works focus on the feature maps of the last convolution layer and pay little attention to the benefits of additional layers. In fact, the feature information hidden in different layers has potential for feature discrimination capacity. The most attention of this work is how to explore the potential of multiple layers from a CNN model. Therefore, this paper proposes multi-layers feature fusion based on CNN and designs a fusion module to solve relevant issues of fusion. In this module, firstly, all the feature maps are transformed to match sizes mutually due to infeasible fusion of feature maps with different scales; then, two fusion methods are introduced to integrate feature maps from different layers instead of the last convolution layer only; finally, the fusion of features are delivered to the next layer or classifier as the routine CNN does. The experimental results show that the suggested methods achieve promising performance on public datasets.

Remote sensing scene classification is still a challenging task. Extracting features effectively from restricted existing labeled data is key to scene classification. Convolutional neural networks (CNNs) are an effective method of constructing discriminating feature representation. However, CNNs usually utilize the feature map from the last layer and ignore additional layers with valuable feature information. In addition, the direct integration of multiple layers brings only a small improvement due to feature redundancy and destruction. To explore the potential information from additional layers and improve the effect of feature fusion, we propose multilayer feature fusion accesses with weight adjustment based on a CNN. We construct access to deliver additional features to one layer to achieve feature fusion and set weight factors to adjust the fusion degree to reduce feature redundancy and destruction. We perform experiments on two common data sets, which indicate improved accuracies and advantages of the extraction capability of our method.

Meta-learning is an effective way to deal with the few-shot problem that only very few annotated data samples are available for training the model. In remote sensing scene classification, previous methods with meta-learning often apply a shallow neural network due to lacking sufficient annotated training data that can support the larger number of parameters of a deep neural network (DNN). However, it is a common phenomenon that a DNN can bring more improvement than a shallow neural network. To this end, we propose a meta-learning method based on parameter transfer. Specifically, we firstly apply parameter transfer to fix the parameters in a DNN to relax the problem of training the large number of parameters. In detail, two variants of parameter transfer are designed to adapt to two different conditions about available annotated data samples, including applying supervised learning for normal meta-training and applying unsupervised domain adaptation for even less meta-training data. Then, the model uses a simple trimming operation to make a minor overhaul on the fixed parameters, which avoids updating the large number of parameters but obtains significant improvement. We perform experiments on three common datasets to demonstrate the improved accuracies and advantages of the feature extraction capability of our method.

The object detectors based on deep convolution neural network have achieved significant success in the field of remote sensing images. Intersection over Union (IoU) and No-maximum suppression (NMS) are the essential components of state-of-the-art anchor-based object detectors. However, as a localization evaluation metric, IoU does not precisely match the boundary box regression, leading to inaccurate regression of the object detector. Therefore, we introduce Hausdorff distance and combine it with IoU as a new evaluation metric (HIoU). NMS is an integral part of the object detection pipeline. However, it may lose relatively small object information in the case of high overlap. Because of the denseness of objects, this defect is more prominent in remote sensing image object detection. Therefore, we consider the context information of location confidence and propose the context maximum selection NMS (Cms-NMS) algorithm. Finally, we integrate HIoU and Cms-NMS into state-of-the-art object detectors, respectively. The performance of these object detectors is improved on the benchmark datasets NWPUVHR-10 and RSOD without any additional hyperparameters. The experiments show that HIoU and Cms-NMS are compatible, and using them together can further improve the detectors' accuracy.