scholarly journals CLRS: Continual Learning Benchmark for Remote Sensing Image Scene Classification

Sensors ◽  
2020 ◽  
Vol 20 (4) ◽  
pp. 1226
Author(s):  
Haifeng Li ◽  
Hao Jiang ◽  
Xin Gu ◽  
Jian Peng ◽  
Wenbo Li ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
Remote Sensing Data ◽  
Remote Sensing Image ◽  
Classification Model ◽  
Scene Classification ◽  
Learning Scenarios ◽  
Batch Data ◽  
Classification Database ◽  
Continual Learning

Remote sensing image scene classification has a high application value in the agricultural, military, as well as other fields. A large amount of remote sensing data is obtained every day. After learning the new batch data, scene classification algorithms based on deep learning face the problem of catastrophic forgetting, that is, they cannot maintain the performance of the old batch data. Therefore, it has become more and more important to ensure that the scene classification model has the ability of continual learning, that is, to learn new batch data without forgetting the performance of the old batch data. However, the existing remote sensing image scene classification datasets all use static benchmarks and lack the standard to divide the datasets into a number of sequential learning training batches, which largely limits the development of continual learning in remote sensing image scene classification. First, this study gives the criteria for training batches that have been partitioned into three continual learning scenarios, and proposes a large-scale remote sensing image scene classification database called the Continual Learning Benchmark for Remote Sensing (CLRS). The goal of CLRS is to help develop state-of-the-art continual learning algorithms in the field of remote sensing image scene classification. In addition, in this paper, a new method of constructing a large-scale remote sensing image classification database based on the target detection pretrained model is proposed, which can effectively reduce manual annotations. Finally, several mainstream continual learning methods are tested and analyzed under three continual learning scenarios, and the results can be used as a baseline for future work.

scholarly journals Project Gradient Descent Adversarial Attack against Multisource Remote Sensing Image Scene Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Yan Jiang ◽  
Guisheng Yin ◽  
Ye Yuan ◽  
Qingan Da
Keyword(s):  
Remote Sensing ◽  
Gradient Descent ◽  
Remote Sensing Data ◽  
Remote Sensing Image ◽  
Descent Method ◽  
Gradient Descent Method ◽  
Learning Technology ◽  
Scene Classification ◽  
Security Threat ◽  
Projected Gradient Descent

Deep learning technology (a deeper and optimized network structure) and remote sensing imaging (i.e., the more multisource and the more multicategory remote sensing data) have developed rapidly. Although the deep convolutional neural network (CNN) has achieved state-of-the-art performance on remote sensing image (RSI) scene classification, the existence of adversarial attacks poses a potential security threat to the RSI scene classification task based on CNN. The corresponding adversarial samples can be generated by adding a small perturbation to the original images. Feeding the CNN-based classifier with the adversarial samples leads to the classifier misclassify with high confidence. To achieve a higher attack success rate against scene classification based on CNN, we introduce the projected gradient descent method to generate adversarial remote sensing images. Then, we select several mainstream CNN-based classifiers as the attacked models to demonstrate the effectiveness of our method. The experimental results show that our proposed method can dramatically reduce the classification accuracy under untargeted and targeted attacks. Furthermore, we also evaluate the quality of the generated adversarial images by visual and quantitative comparisons. The results show that our method can generate the imperceptible adversarial samples and has a stronger attack ability for the RSI scene classification.

scholarly journals Cohesion Intensive Deep Hashing for Remote Sensing Image Retrieval

2019 ◽  
Vol 12 (1) ◽  
pp. 101 ◽  
Author(s):  
Lirong Han ◽  
Peng Li ◽  
Xiao Bai ◽  
Christos Grecos ◽  
Xiaoyu Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Image Retrieval ◽  
Large Scale ◽  
Remote Sensing Data ◽  
Optimization Method ◽  
Remote Sensing Image ◽  
Model Parameters ◽  
Remote Sensing Images ◽  
Deep Hashing ◽  
Deep Model

Recently, the demand for remote sensing image retrieval is growing and attracting the interest of many researchers because of the increasing number of remote sensing images. Hashing, as a method of retrieving images, has been widely applied to remote sensing image retrieval. In order to improve hashing performance, we develop a cohesion intensive deep hashing model for remote sensing image retrieval. The underlying architecture of our deep model is motivated by the state-of-the-art residual net. Residual nets aim at avoiding gradient vanishing and gradient explosion when the net reaches a certain depth. However, different from the residual net which outputs multiple class-labels, we present a residual hash net that is terminated by a Heaviside-like function for binarizing remote sensing images. In this scenario, the representational power of the residual net architecture is exploited to establish an end-to-end deep hashing model. The residual hash net is trained subject to a weighted loss strategy that intensifies the cohesiveness of image hash codes within one class. This effectively addresses the data imbalance problem normally arising in remote sensing image retrieval tasks. Furthermore, we adopted a gradualness optimization method for obtaining optimal model parameters in order to favor accurate binary codes with little quantization error. We conduct comparative experiments on large-scale remote sensing data sets such as UCMerced and AID. The experimental results validate the hypothesis that our method improves the performance of current remote sensing image retrieval.

scholarly journals High Spatial Resolution Remote Sensing Data Classification Method Based on Spectrum Sharing

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Meimei Duan ◽  
Lijuan Duan
Keyword(s):  
Remote Sensing ◽  
Spatial Resolution ◽  
Spectrum Sharing ◽  
High Spatial Resolution ◽  
Remote Sensing Data ◽  
Data Classification ◽  
Remote Sensing Image ◽  
Classification Model ◽  
Classification Method ◽  
Sensing Data

Existing remote sensing data classification methods cannot achieve the sharing of remote sensing image spectrum, leading to poor fusion and classification of remote sensing data. Therefore, a high spatial resolution remote sensing data classification method based on spectrum sharing is proposed. A page frame recovery algorithm (PFRA) is introduced to allocate the wireless spectrum resources in low-frequency band, and a dynamic spectrum sharing mechanism is designed between the primary and secondary users of remote sensing images. Based on this, D-S evidence theory is used to fuse high spatial resolution remote sensing data and correct the pixel brightness of the fused multispectral image. The initial data are normalized, the feature of spectral image is extracted, the convolution neural network classification model is constructed, and the remote sensing image is segmented. Experimental results show that the proposed method takes shorter time and has higher accuracy for high spatial resolution image segmentation. High spatial resolution remote sensing data classification is more efficient, and the accuracy of data classification and remote sensing image fusion are more ideal.

scholarly journals REMOTE SENSING IMAGE CLASSIFICATION WITH THE SEN12MS DATASET

2021 ◽  
Vol V-2-2021 ◽  
pp. 101-106
Author(s):  
M. Schmitt ◽  
Y.-L. Wu
Keyword(s):  
Remote Sensing ◽  
Computer Vision ◽  
Image Classification ◽  
Large Scale ◽  
High Capacity ◽  
Remote Sensing Image ◽  
Sensor Data ◽  
Scene Classification ◽  
Multi Sensor Data Fusion ◽  
Remote Sensing Image Classification

Abstract. Image classification is one of the main drivers of the rapid developments in deep learning with convolutional neural networks for computer vision. So is the analogous task of scene classification in remote sensing. However, in contrast to the computer vision community that has long been using well-established, large-scale standard datasets to train and benchmark high-capacity models, the remote sensing community still largely relies on relatively small and often application-dependend datasets, thus lacking comparability. With this paper, we present a classification-oriented conversion of the SEN12MS dataset. Using that, we provide results for several baseline models based on two standard CNN architectures and different input data configurations. Our results support the benchmarking of remote sensing image classification and provide insights to the benefit of multi-spectral data and multi-sensor data fusion over conventional RGB imagery.

scholarly journals Remote Sensing Image Scene Classification with Noisy Label Distillation

2020 ◽  
Vol 12 (15) ◽  
pp. 2376
Author(s):  
Rui Zhang ◽  
Zhenghao Chen ◽  
Sanxing Zhang ◽  
Fei Song ◽  
Gang Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
Low Cost ◽  
Full Range ◽  
Remote Sensing Image ◽  
Rapid Expansion ◽  
Fine Tuning ◽  
Distillation Method ◽  
Scene Classification ◽  
Teacher Student

The widespread applications of remote sensing image scene classification-based Convolutional Neural Networks (CNNs) are severely affected by the lack of large-scale datasets with clean annotations. Data crawled from the Internet or other sources allows for the most rapid expansion of existing datasets at a low-cost. However, directly training on such an expanded dataset can lead to network overfitting to noisy labels. Traditional methods typically divide this noisy dataset into multiple parts. Each part fine-tunes the network separately to improve performance further. These approaches are inefficient and sometimes even hurt performance. To address these problems, this study proposes a novel noisy label distillation method (NLD) based on the end-to-end teacher-student framework. First, unlike general knowledge distillation methods, NLD does not require pre-training on clean or noisy data. Second, NLD effectively distills knowledge from labels across a full range of noise levels for better performance. In addition, NLD can benefit from a fully clean dataset as a model distillation method to improve the student classifier’s performance. NLD is evaluated on three remote sensing image datasets, including UC Merced Land-use, NWPU-RESISC45, AID, in which a variety of noise patterns and noise amounts are injected. Experimental results show that NLD outperforms widely used directly fine-tuning methods and remote sensing pseudo-labeling methods.

scholarly journals RESEARCH ON SE-INCEPTION IN HIGH-RESOLUTION REMOTE SENSING IMAGE CLASSIFICATION

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 539-545
Author(s):  
Z. L. Cai ◽  
Q. Weng ◽  
S. Z. Ye
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
High Resolution ◽  
Transfer Learning ◽  
Network Performance ◽  
Learning Strategy ◽  
Remote Sensing Image ◽  
Classification Model ◽  
Learning Networks ◽  
Scene Classification

Abstract. With the deepening research and cross-fusion in the modern remote sensing image area, the classification of high spatial resolution remote sensing images has captured the attention of the researchers in the field of remote sensing. However, due to the serious phenomenon of “same object, different spectrum” and “same spectrum, different object” of high-resolution remote sensing image, the traditional classification strategy is hard to handle this challenge. In this paper, a remote sensing image scene classification model based on SENet and Inception-V3 is proposed by utilizing the deep learning method and transfer learning strategy. The model first adds a dropout layer before the full connection layer of the original Inception-V3 model to avoid over-fitting. Then we embed the SENet module into the Inception-V3 model for optimizing the network performance. In this paper, global average pooling is used as squeeze operation, and then two fully connected layers are used to construct a bottleneck structure. The model proposed in this paper is more non-linear, can better fit the complex correlation between channels, and greatly reduces the amount of parameters and computation. In the training process, this paper adopts the transfer learning strategy, makes full use of existing models and knowledge, improves training efficiency, and finally obtains scene classification results. The experimental results based on AID high-score remote sensing scene images show that SE-Inception has faster convergence speed and more stable training effect than the original Inception-V3 training. Compared with other traditional methods and deep learning networks, the improved model proposed in this paper has greater accuracy improvement.

MILL: Channel Attention–based Deep Multiple Instance Learning for Landslide Recognition

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-11
Author(s):  
Xiaochuan Tang ◽  
Mingzhe Liu ◽  
Hao Zhong ◽  
Yuanzhen Ju ◽  
Weile Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Large Scale ◽  
Remote Sensing Image ◽  
Disaster Risk ◽  
Multiple Instance Learning ◽  
Remote Sensing Images ◽  
Loess Area ◽  
Remote Sensing Image Classification ◽  
Natural Disaster Risk

Landslide recognition is widely used in natural disaster risk management. Traditional landslide recognition is mainly conducted by geologists, which is accurate but inefficient. This article introduces multiple instance learning (MIL) to perform automatic landslide recognition. An end-to-end deep convolutional neural network is proposed, referred to as Multiple Instance Learning–based Landslide classification (MILL). First, MILL uses a large-scale remote sensing image classification dataset to build pre-train networks for landslide feature extraction. Second, MILL extracts instances and assign instance labels without pixel-level annotations. Third, MILL uses a new channel attention–based MIL pooling function to map instance-level labels to bag-level label. We apply MIL to detect landslides in a loess area. Experimental results demonstrate that MILL is effective in identifying landslides in remote sensing images.

scholarly journals Quantitative Recognition and Characteristic Analysis of Production-Living-Ecological Space Evolution for Five Resource-Based Cities: Zululand, Xuzhou, Lota, Surf Coast and Ruhr

2021 ◽  
Vol 13 (8) ◽  
pp. 1563
Author(s):  
Yuanyuan Tao ◽  
Qianxin Wang
Keyword(s):  
Remote Sensing ◽  
Urban Areas ◽  
Large Scale ◽  
Remote Sensing Image ◽  
Data Availability ◽  
Function Evaluation ◽  
Characteristic Analysis ◽  
Accurate Identification ◽  
Living Space ◽  
Evolution Characteristics

The accurate identification of PLES changes and the discovery of their evolution characteristics is a key issue to improve the ability of the sustainable development for resource-based urban areas. However, the current methods are unsuitable for the long-term and large-scale PLES investigation. In this study, a modified method of PLES recognition is proposed based on the remote sensing image classification and land function evaluation technology. A multi-dimensional index system is constructed, which can provide a comprehensive evaluation for PLES evolution characteristics. For validation of the proposed methods, the remote sensing image, geographic information, and socio-economic data of five resource-based urbans (Zululand in South Africa, Xuzhou in China, Lota in Chile, Surf Coast in Australia, and Ruhr in Germany) from 1975 to 2020 are collected and tested. The results show that the data availability and calculation efficiency are significantly improved by the proposed method, and the recognition precision is better than 87% (Kappa coefficient). Furthermore, the PLES evolution characteristics show obvious differences at the different urban development stages. The expansions of production, living, and ecological space are fastest at the mining, the initial, and the middle ecological restoration stages, respectively. However, the expansion of living space is always increasing at any stage, and the disorder expansion of living space has led to the decrease of integration of production and ecological spaces. Therefore, the active polices should be formulated to guide the transformation of the living space expansion from jumping-type and spreading-type to filling-type, and the renovation of abandoned industrial and mining lands should be encouraged.

Sign in / Sign up

Export Citation Format

Share Document