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 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 Distribution Consistency Loss for Large-Scale Remote Sensing Image Retrieval

2020 ◽  
Vol 12 (1) ◽  
pp. 175 ◽  
Author(s):  
Lili Fan ◽  
Hongwei Zhao ◽  
Haoyu Zhao
Keyword(s):  
Remote Sensing ◽  
Image Retrieval ◽  
Large Scale ◽  
Metric Learning ◽  
Remote Sensing Image ◽  
Positive Sample ◽  
Fine Tuning ◽  
Remote Sensing Images ◽  
Hard Samples ◽  
Image Datasets

Remote sensing images are featured by massiveness, diversity and complexity. These features put forward higher requirements for the speed and accuracy of remote sensing image retrieval. The extraction method plays a key role in retrieving remote sensing images. Deep metric learning (DML) captures the semantic similarity information between data points by learning embedding in vector space. However, due to the uneven distribution of sample data in remote sensing image datasets, the pair-based loss currently used in DML is not suitable. To improve this, we propose a novel distribution consistency loss to solve this problem. First, we define a new way to mine samples by selecting five in-class hard samples and five inter-class hard samples to form an informative set. This method can make the network extract more useful information in a short time. Secondly, in order to avoid inaccurate feature extraction due to sample imbalance, we assign dynamic weight to the positive samples according to the ratio of the number of hard samples and easy samples in the class, and name the loss caused by the positive sample as the sample balance loss. We combine the sample balance of the positive samples with the ranking consistency of the negative samples to form our distribution consistency loss. Finally, we built an end-to-end fine-tuning network suitable for remote sensing image retrieval. We display comprehensive experimental results drawing on three remote sensing image datasets that are publicly available and show that our method achieves the state-of-the-art performance.

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.

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.

Marginal Center Loss for Deep Remote Sensing Image Scene Classification

2020 ◽  
Vol 17 (6) ◽  
pp. 968-972 ◽  
Author(s):  
Tianyu Wei ◽  
Jue Wang ◽  
Wenchao Liu ◽  
He Chen ◽  
Hao Shi
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Image ◽  
Scene Classification ◽  
Center Loss

scholarly journals A Multi-Branch Feature Fusion Strategy Based on an Attention Mechanism for Remote Sensing Image Scene Classification

2021 ◽  
Vol 13 (10) ◽  
pp. 1950
Author(s):  
Cuiping Shi ◽  
Xin Zhao ◽  
Liguo Wang
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
Classification Accuracy ◽  
Feature Fusion ◽  
State Of The Art ◽  
Rapid Development ◽  
Remote Sensing Image ◽  
Classification Performance ◽  
Attention Mechanism ◽  
Scene Classification

In recent years, with the rapid development of computer vision, increasing attention has been paid to remote sensing image scene classification. To improve the classification performance, many studies have increased the depth of convolutional neural networks (CNNs) and expanded the width of the network to extract more deep features, thereby increasing the complexity of the model. To solve this problem, in this paper, we propose a lightweight convolutional neural network based on attention-oriented multi-branch feature fusion (AMB-CNN) for remote sensing image scene classification. Firstly, we propose two convolution combination modules for feature extraction, through which the deep features of images can be fully extracted with multi convolution cooperation. Then, the weights of the feature are calculated, and the extracted deep features are sent to the attention mechanism for further feature extraction. Next, all of the extracted features are fused by multiple branches. Finally, depth separable convolution and asymmetric convolution are implemented to greatly reduce the number of parameters. The experimental results show that, compared with some state-of-the-art methods, the proposed method still has a great advantage in classification accuracy with very few parameters.

scholarly journals Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3232 ◽  
Author(s):  
Yan Liu ◽  
Qirui Ren ◽  
Jiahui Geng ◽  
Meng Ding ◽  
Jiangyun Li
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Large Scale ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Training Data ◽  
Land Resources ◽  
Remote Sensing Images ◽  
Training Strategy ◽  
The Impact

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation.

Sign in / Sign up

Export Citation Format

Share Document