scholarly journals Domain Adaptation for Semantic Segmentation of Historical Panchromatic Orthomosaics in Central Africa

2021 ◽  
Vol 10 (8) ◽  
pp. 523
Author(s):  
Nicholus Mboga ◽  
Stefano D’Aronco ◽  
Tais Grippa ◽  
Charlotte Pelletier ◽  
Stefanos Georganos ◽  
...  
Keyword(s):  
Land Cover ◽  
Domain Adaptation ◽  
Central Africa ◽  
Semantic Segmentation ◽  
Target Domain ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
The Cost ◽  
Performance Gains

Multitemporal environmental and urban studies are essential to guide policy making to ultimately improve human wellbeing in the Global South. Land-cover products derived from historical aerial orthomosaics acquired decades ago can provide important evidence to inform long-term studies. To reduce the manual labelling effort by human experts and to scale to large, meaningful regions, we investigate in this study how domain adaptation techniques and deep learning can help to efficiently map land cover in Central Africa. We propose and evaluate a methodology that is based on unsupervised adaptation to reduce the cost of generating reference data for several cities and across different dates. We present the first application of domain adaptation based on fully convolutional networks for semantic segmentation of a dataset of historical panchromatic orthomosaics for land-cover generation for two focus cities Goma-Gisenyi and Bukavu. Our experimental evaluation shows that the domain adaptation methods can reach an overall accuracy between 60% and 70% for different regions. If we add a small amount of labelled data from the target domain, too, further performance gains can be achieved.

scholarly journals Unsupervised Domain Expansion for Visual Categorization

2021 ◽  
Vol 17 (4) ◽  
pp. 1-24
Author(s):  
Jie Wang ◽  
Kaibin Tian ◽  
Dayong Ding ◽  
Gang Yang ◽  
Xirong Li
Keyword(s):  
Domain Adaptation ◽  
Unlabeled Data ◽  
Target Domain ◽  
Source Domain ◽  
Visual Categorization ◽  
Performance Loss ◽  
Deep Model ◽  
Knowledge Distillation ◽  
The Cost

Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA). Given labeled data from a source domain and unlabeled data from a target domain, UDA seeks for a deep representation that is both discriminative and domain-invariant. While UDA focuses on the target domain, we argue that the performance on both source and target domains matters, as in practice which domain a test example comes from is unknown. In this article, we extend UDA by proposing a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model’s performance on the source domain. We propose Knowledge Distillation Domain Expansion (KDDE) as a general method for the UDE task. Its domain-adaptation module can be instantiated with any existing model. We develop a knowledge distillation-based learning mechanism, enabling KDDE to optimize a single objective wherein the source and target domains are equally treated. Extensive experiments on two major benchmarks, i.e., Office-Home and DomainNet, show that KDDE compares favorably against four competitive baselines, i.e., DDC, DANN, DAAN, and CDAN, for both UDA and UDE tasks. Our study also reveals that the current UDA models improve their performance on the target domain at the cost of noticeable performance loss on the source domain.

scholarly journals From shallow to deep: exploiting feature-based classifiers for domain adaptation in semantic segmentation

2021 ◽  
Author(s):  
Alex Matskevych ◽  
Adrian Wolny ◽  
Constantin Pape ◽  
Anna Kreshuk
Keyword(s):  
Random Forest ◽  
Domain Adaptation ◽  
Semantic Segmentation ◽  
Training Data ◽  
Target Domain ◽  
Segmentation Accuracy ◽  
Challenging Tasks ◽  
Feature Based ◽  
The Cost ◽  
Nuclear Segmentation

The remarkable performance of Convolutional Neural Networks on image segmentation tasks comes at the cost of a large amount of pixelwise annotated images that have to be segmented for training. In contrast, feature-based learning methods, such as the Random Forest, require little training data, but never reach the segmentation accuracy of CNNs. This work bridges the two approaches in a transfer learning setting. We show that a CNN can be trained to correct the errors of the Random Forest in the source domain and then be applied to correct such errors in the target domain without retraining, as the domain shift between the Random Forest predictions is much smaller than between the raw data. By leveraging a few brushstrokes as annotations in the target domain, the method can deliver segmentations that are sufficiently accurate to act as pseudo-labels for target-domain CNN training. We demonstrate the performance of the method on several datasets with the challenging tasks of mitochondria, membrane and nuclear segmentation. It yields excellent performance compared to microscopy domain adaptation baselines, especially when a significant domain shift is involved.

scholarly journals Data-Efficient Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Generative Adversarial Networks

2020 ◽  
Vol 10 (3) ◽  
pp. 1092 ◽  
Author(s):  
Bilel Benjdira ◽  
Adel Ammar ◽  
Anis Koubaa ◽  
Kais Ouni
Keyword(s):  
Domain Adaptation ◽  
Semantic Segmentation ◽  
Aerial Imagery ◽  
Generative Adversarial Networks ◽  
Target Domain ◽  
Source Domain ◽  
Adversarial Networks ◽  
Semantic Label ◽  
Global Accuracy ◽  
The Cost

Despite the significant advances noted in semantic segmentation of aerial imagery, a considerable limitation is blocking its adoption in real cases. If we test a segmentation model on a new area that is not included in its initial training set, accuracy will decrease remarkably. This is caused by the domain shift between the new targeted domain and the source domain used to train the model. In this paper, we addressed this challenge and proposed a new algorithm that uses Generative Adversarial Networks (GAN) architecture to minimize the domain shift and increase the ability of the model to work on new targeted domains. The proposed GAN architecture contains two GAN networks. The first GAN network converts the chosen image from the target domain into a semantic label. The second GAN network converts this generated semantic label into an image that belongs to the source domain but conserves the semantic map of the target image. This resulting image will be used by the semantic segmentation model to generate a better semantic label of the first chosen image. Our algorithm is tested on the ISPRS semantic segmentation dataset and improved the global accuracy by a margin up to 24% when passing from Potsdam domain to Vaihingen domain. This margin can be increased by addition of other labeled data from the target domain. To minimize the cost of supervision in the translation process, we proposed a methodology to use these labeled data efficiently.

scholarly journals Automatic Deep Learning Semantic Segmentation of Ultrasound Thyroid Cineclips using Recurrent Fully Convolutional Networks

IEEE Access ◽  
2020 ◽  
pp. 1-1
Author(s):  
Jeremy M. Webb ◽  
Duane D. Meixner ◽  
Shaheeda A. Adusei ◽  
Eric C. Polley ◽  
Mostafa Fatemi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Semantic Segmentation ◽  
Convolutional Networks ◽  
Fully Convolutional Networks

scholarly journals USING SEMANTICALLY PAIRED IMAGES TO IMPROVE DOMAIN ADAPTATION FOR THE SEMANTIC SEGMENTATION OF AERIAL IMAGES

2020 ◽  
Vol V-2-2020 ◽  
pp. 483-492
Author(s):  
D. Gritzner ◽  
J. Ostermann
Keyword(s):  
Time Window ◽  
Domain Adaptation ◽  
Geographical Area ◽  
Model Performance ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Training Data ◽  
Aerial Images ◽  
Target Domain ◽  
Training Examples

Abstract. Modern machine learning, especially deep learning, which is used in a variety of applications, requires a lot of labelled data for model training. Having an insufficient amount of training examples leads to models which do not generalize well to new input instances. This is a particular significant problem for tasks involving aerial images: often training data is only available for a limited geographical area and a narrow time window, thus leading to models which perform poorly in different regions, at different times of day, or during different seasons. Domain adaptation can mitigate this issue by using labelled source domain training examples and unlabeled target domain images to train a model which performs well on both domains. Modern adversarial domain adaptation approaches use unpaired data. We propose using pairs of semantically similar images, i.e., whose segmentations are accurate predictions of each other, for improved model performance. In this paper we show that, as an upper limit based on ground truth, using semantically paired aerial images during training almost always increases model performance with an average improvement of 4.2% accuracy and .036 mean intersection-over-union (mIoU). Using a practical estimate of semantic similarity, we still achieve improvements in more than half of all cases, with average improvements of 2.5% accuracy and .017 mIoU in those cases.

scholarly journals Dual Path Attention Net for Remote Sensing Semantic Image Segmentation

2020 ◽  
Vol 9 (10) ◽  
pp. 571
Author(s):  
Jinglun Li ◽  
Jiapeng Xiu ◽  
Zhengqiu Yang ◽  
Chen Liu
Keyword(s):  
Remote Sensing ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
Remote Sensing Images ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Augmentation Strategies ◽  
Rich Information ◽  
The Mean ◽  
The Rich

Semantic segmentation plays an important role in being able to understand the content of remote sensing images. In recent years, deep learning methods based on Fully Convolutional Networks (FCNs) have proved to be effective for the sematic segmentation of remote sensing images. However, the rich information and complex content makes the training of networks for segmentation challenging, and the datasets are necessarily constrained. In this paper, we propose a Convolutional Neural Network (CNN) model called Dual Path Attention Network (DPA-Net) that has a simple modular structure and can be added to any segmentation model to enhance its ability to learn features. Two types of attention module are appended to the segmentation model, one focusing on spatial information the other focusing upon the channel. Then, the outputs of these two attention modules are fused to further improve the network’s ability to extract features, thus contributing to more precise segmentation results. Finally, data pre-processing and augmentation strategies are used to compensate for the small number of datasets and uneven distribution. The proposed network was tested on the Gaofen Image Dataset (GID). The results show that the network outperformed U-Net, PSP-Net, and DeepLab V3+ in terms of the mean IoU by 0.84%, 2.54%, and 1.32%, respectively.

scholarly journals Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

2019 ◽  
Vol 11 (10) ◽  
pp. 1153 ◽  
Author(s):  
Mesay Belete Bejiga ◽  
Farid Melgani ◽  
Pietro Beraldini
Keyword(s):  
Neural Networks ◽  
Land Cover ◽  
Transfer Learning ◽  
Large Scale ◽  
Domain Adaptation ◽  
Land Cover Classification ◽  
Target Domain ◽  
Training Samples ◽  
Latent Space ◽  
Large Scale Land

Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.

Sign in / Sign up

Export Citation Format

Share Document