High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks

Abstract

Class imbalance is a key issue for the application of deep learning for remote sensing image classification because a model generated by imbalanced samples training has low classification accuracy for minority classes. In this study, an accurate classification approach using the multistage sampling method and deep neural networks was proposed to classify imbalanced data. We first balance samples by multistage sampling to obtain the training sets. Then, a state-of-the-art model is adopted by combining the advantages of atrous spatial pyramid pooling (ASPP) and Encoder-Decoder for pixel-wise classification, which are two different types of fully convolutional networks (FCNs) that can obtain contextual information of multiple levels in the Encoder stage. The details and spatial dimensions of targets are restored using such information during the Decoder stage. We employ four deep learning-based classification algorithms (basic FCN, FCN-8S, ASPP, and Encoder-Decoder with ASPP of our approach) on multistage training sets (original, MUS1, and MUS2) of WorldView-3 images in southeastern Qinghai-Tibet Plateau and GF-2 images in northeastern Beijing for comparison. The experiments show that, compared with existing sets (original, MUS1, and identical) and existing method (cost weighting), the MUS2 training set of multistage sampling significantly enhance the classification performance for minority classes. Our approach shows distinct advantages for imbalanced data.

Remote Sensing Image Semantic Segmentation Based on Edge Information Guidance

“…The mean value further proves the superiority of the proposed algorithms compared with FCN. Standard deviation reveals imbalance in segmentation between different classes [15]. It can be seen that the standard deviations of these three algorithms are all relatively high due to small amount of image data, even if the proposed algorithm does not improve this problem well.…”

“…[14] introduces atrous convolution in high-resolution remote sensing image classification. Moreover, Atrous Spatial Pyramid Pooling (ASPP) implemented in Deeplab-V2 [6] is also used in remote sensing image classification [15].…”

Landslide Extraction from High-Resolution Remote Sensing Imagery Using Fully Convolutional Spectral–Topographic Fusion Network

“…In the data-preparation stage (Figure 1a), the image data, slope, aspect, NDVI data, and labeled data were sliced into small patches using superpixel segmentation. Meanwhile, the multistage sampling 16 [34] method was employed to ensure that the sample proportions of various classes were relatively balanced. In the training stage, training samples were input to the proposed FSTF-net network (Figure 1b), and the stochastic gradient descent (SDG) was used to update network parameters.…”

Fusion High-Resolution Network for Diagnosing ChestX-ray Images

“…The ChestX-ray image of a patient needs to be read by a senior radiologist for at least 10 min to make a diagnosis and different doctors can make inconsistent diagnoses of the same ChestX-ray image, which means that the results are affected by the cognitive ability of the radiologist, subjective experience, fatigue and other factors [2]. Computer-aided diagnosis (CAD) can overcome the deficiencies of radiologists, make Recently, benefitting from deep learning techniques [6], computer vision [7] has had remarkable success in the fields of target detection [8], image classification [9,10] and image inpainting [11], for example. This notable progress has led to the development of many medical image processing applications, including disease classification [12], lesion detection or segmentation [13][14][15], registration [16], image annotation [17,18] as well as other examples [19].…”