scholarly journals SSDAN: Multi-Source Semi-Supervised Domain Adaptation Network for Remote Sensing Scene Classification

2021 ◽  
Vol 13 (19) ◽  
pp. 3861
Author(s):  
Tariq Lasloum ◽  
Haikel Alhichri ◽  
Yakoub Bazi ◽  
Naif Alajlan
Keyword(s):  
Remote Sensing ◽  
Loss Function ◽  
Domain Adaptation ◽  
Activation Function ◽  
Cross Entropy ◽  
Scene Classification ◽  
Entropy Loss ◽  
Training Approach ◽  
Temperature Parameter ◽  
And Control

We present a new method for multi-source semi-supervised domain adaptation in remote sensing scene classification. The method consists of a pre-trained convolutional neural network (CNN) model, namely EfficientNet-B3, for the extraction of highly discriminative features, followed by a classification module that learns feature prototypes for each class. Then, the classification module computes a cosine distance between feature vectors of target data samples and the feature prototypes. Finally, the proposed method ends with a Softmax activation function that converts the distances into class probabilities. The feature prototypes are also divided by a temperature parameter to normalize and control the classification module. The whole model is trained on both the unlabeled and labeled target samples. It is trained to predict the correct classes utilizing the standard cross-entropy loss computed over the labeled source and target samples. At the same time, the model is trained to learn domain invariant features using another loss function based on entropy computed over the unlabeled target samples. Unlike the standard cross-entropy loss, the new entropy loss function is computed on the model’s predicted probabilities and does not need the true labels. This entropy loss, called minimax loss, needs to be maximized with respect to the classification module to learn features that are domain-invariant (hence removing the data shift), and at the same time, it should be minimized with respect to the CNN feature extractor to learn discriminative features that are clustered around the class prototypes (in other words reducing intra-class variance). To accomplish these maximization and minimization processes at the same time, we use an adversarial training approach, where we alternate between the two processes. The model combines the standard cross-entropy loss and the new minimax entropy loss and optimizes them jointly. The proposed method is tested on four RS scene datasets, namely UC Merced, AID, RESISC45, and PatternNet, using two-source and three-source domain adaptation scenarios. The experimental results demonstrate the strong capability of the proposed method to achieve impressive performance despite using only a few (six in our case) labeled target samples per class. Its performance is already better than several state-of-the-art methods, including RevGrad, ADDA, Siamese-GAN, and MSCN.

scholarly journals AttentionBased Deep Feature Fusion for the Scene Classification of HighResolution Remote Sensing Images

2019 ◽  
Vol 11 (17) ◽  
pp. 1996 ◽  
Author(s):  
Zhu ◽  
Yan ◽  
Mo ◽  
Liu
Keyword(s):  
Remote Sensing ◽  
Loss Function ◽  
Feature Fusion ◽  
Cross Entropy ◽  
Scene Classification ◽  
Remote Sensing Images ◽  
Graphic Processing Units ◽  
Entropy Loss ◽  
Deep Feature

Scene classification of highresolution remote sensing images (HRRSI) is one of the most important means of landcover classification. Deep learning techniques, especially the convolutional neural network (CNN) have been widely applied to the scene classification of HRRSI due to the advancement of graphic processing units (GPU). However, they tend to extract features from the whole images rather than discriminative regions. The visual attention mechanism can force the CNN to focus on discriminative regions, but it may suffer from the influence of intraclass diversity and repeated texture. Motivated by these problems, we propose an attention-based deep feature fusion (ADFF) framework that constitutes three parts, namely attention maps generated by Gradientweighted Class Activation Mapping (GradCAM), a multiplicative fusion of deep features and the centerbased cross-entropy loss function. First of all, we propose to make attention maps generated by GradCAM as an explicit input in order to force the network to concentrate on discriminative regions. Then, deep features derived from original images and attention maps are proposed to be fused by multiplicative fusion in order to consider both improved abilities to distinguish scenes of repeated texture and the salient regions. Finally, the centerbased cross-entropy loss function that utilizes both the cross-entropy loss and center loss function is proposed to backpropagate fused features so as to reduce the effect of intraclass diversity on feature representations. The proposed ADFF architecture is tested on three benchmark datasets to show its performance in scene classification. The experiments confirm that the proposed method outperforms most competitive scene classification methods with an average overall accuracy of 94% under different training ratios.

scholarly journals Domain Adaptation for Convolutional Neural Networks-Based Remote Sensing Scene Classification

2019 ◽  
Vol 16 (8) ◽  
pp. 1324-1328 ◽  
Author(s):  
Shaoyue Song ◽  
Hongkai Yu ◽  
Zhenjiang Miao ◽  
Qiang Zhang ◽  
Yuewei Lin ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Domain Adaptation ◽  
Scene Classification

scholarly journals MRSSC: A BENCHMARK DATASET FOR MULTIMODAL REMOTE SENSING SCENE CLASSIFICATION

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 785-792
Author(s):  
K. Liu ◽  
A. Wu ◽  
X. Wan ◽  
S. Li
Keyword(s):  
Remote Sensing ◽  
Domain Adaptation ◽  
Image Interpretation ◽  
Visual Navigation ◽  
Classification Model ◽  
Observation Data ◽  
Scene Classification ◽  
Manned Spacecraft ◽  
Optical Images ◽  
Earth Observation Data

Abstract. Scene classification based on multi-source remote sensing image is important for image interpretation, and has many applications, such as change detection, visual navigation and image retrieval. Deep learning has become a research hotspot in the field of remote sensing scene classification, and dataset is an important driving force to promote its development. Most of the remote sensing scene classification datasets are optical images, and multimodal datasets are relatively rare. Existing datasets that contain both optical and SAR data, such as SARptical and WHU-SEN-City, which mainly focused on urban area without wide variety of scene categories. This largely limits the development of domain adaptive algorithms in remote sensing scene classification. In this paper, we proposed a multi-modal remote sensing scene classification dataset (MRSSC) based on Tiangong-2, a Chinese manned spacecraft which can acquire optical and SAR images at the same time. The dataset contains 12167 images (optical 6155 and 6012 for optical and SAR, resp.) of seven typical scenes, namely city, farmland, mountain, desert, coast, lake and river. Our dataset is evaluated by state-of-theart domain adaptation methods to establish a baseline with average classification accuracy of 79.2%. The MRSSC dataset will be released freely for the educational purpose and can be found at China Manned Space Engineering data service website (http://www.msadc.cn). This dataset will fill the gap between remote sensing scene classification between different image sources, and paves the way for a generalized image classification model for multi-modal earth observation data.

scholarly journals Convolutional Neural Networks with Deep Supervised Feature Learning for Remote Sensing Scene Classification

2020 ◽  
Author(s):  
Grigorios Tsagkatakis ◽  
Panagiotis Tsakalides
Keyword(s):  
Remote Sensing ◽  
Feature Learning ◽  
Ground Truth ◽  
Classification Performance ◽  
Cross Entropy ◽  
Scene Classification ◽  
Feature Representations ◽  
Benchmark Datasets ◽  
Low Dimensional ◽  
Fully Connected

State-of-the-art remote sensing scene classification methods employ different Convolutional Neural Network architectures for achieving very high classification performance. A trait shared by the majority of these methods is that the class associated with each example is ascertained by examining the activations of the last fully connected layer, and the networks are trained to minimize the cross-entropy between predictions extracted from this layer and ground-truth annotations. In this work, we extend this paradigm by introducing an additional output branch which maps the inputs to low dimensional representations, effectively extracting additional feature representations of the inputs. The proposed model imposes additional distance constrains on these representations with respect to identified class representatives, in addition to the traditional categorical cross-entropy between predictions and ground-truth. By extending the typical cross-entropy loss function with a distance learning function, our proposed approach achieves significant gains across a wide set of benchmark datasets in terms of classification, while providing additional evidence related to class membership and classification confidence.

scholarly journals Approximating the Gradient of Cross-Entropy Loss Function

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 111626-111635
Author(s):  
Li Li ◽  
Milos Doroslovacki ◽  
Murray H. Loew
Keyword(s):  
Loss Function ◽  
Cross Entropy ◽  
Entropy Loss

DFENet for Domain Adaptation based Remote Sensing Scene Classification

2021 ◽  
pp. 1-1
Author(s):  
Xiufei Zhang ◽  
Xiwen Yao ◽  
Xiaoxu Feng ◽  
Gong Cheng ◽  
Junwei Han
Keyword(s):  
Remote Sensing ◽  
Domain Adaptation ◽  
Scene Classification

scholarly journals MPCE: A Maximum Probability Based Cross Entropy Loss Function for Neural Network Classification

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 146331-146341 ◽  
Author(s):  
Yangfan Zhou ◽  
Xin Wang ◽  
Mingchuan Zhang ◽  
Junlong Zhu ◽  
Ruijuan Zheng ◽  
...  
Keyword(s):  
Neural Network ◽  
Loss Function ◽  
Cross Entropy ◽  
Maximum Probability ◽  
Entropy Loss ◽  
Neural Network Classification

scholarly journals Shaping the learning landscape in neural networks around wide flat minima

2019 ◽  
Vol 117 (1) ◽  
pp. 161-170 ◽  
Author(s):  
Carlo Baldassi ◽  
Fabrizio Pittorino ◽  
Riccardo Zecchina
Keyword(s):  
Neural Networks ◽  
Loss Function ◽  
Critical Points ◽  
Learning Process ◽  
Numerical Study ◽  
Cross Entropy ◽  
Stochastic Gradient Descent ◽  
Neural Network Models ◽  
Entropy Loss ◽  
Error Loss

Learning in deep neural networks takes place by minimizing a nonconvex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers without getting stuck in local critical points and such minimizers are often satisfactory at avoiding overfitting. How these 2 features can be kept under control in nonlinear devices composed of millions of tunable connections is a profound and far-reaching open question. In this paper we study basic nonconvex 1- and 2-layer neural network models that learn random patterns and derive a number of basic geometrical and algorithmic features which suggest some answers. We first show that the error loss function presents few extremely wide flat minima (WFM) which coexist with narrower minima and critical points. We then show that the minimizers of the cross-entropy loss function overlap with the WFM of the error loss. We also show examples of learning devices for which WFM do not exist. From the algorithmic perspective we derive entropy-driven greedy and message-passing algorithms that focus their search on wide flat regions of minimizers. In the case of SGD and cross-entropy loss, we show that a slow reduction of the norm of the weights along the learning process also leads to WFM. We corroborate the results by a numerical study of the correlations between the volumes of the minimizers, their Hessian, and their generalization performance on real data.

Sign in / Sign up

Export Citation Format

Share Document