Search

In recent years, deep convolutional neural networks (DCNNs) have shown their predominant place in building extraction. Generally, the performance of DCNNs depends on the quality of parameter learning. To improve the performance, many approaches chose to enlarge the network size or employ additional plug-in modules. However, there exists large redundancy in parameter learning of neural networks. We argue that the methods totally relying on parameter learning cannot fully exploit the useful information of the given data, and feature learned by such methods is not comprehensive enough. In this paper, we propose an efficient memory module, named EMM , to enhance the learning ability of DCNNs in building extraction. In our method, we encode each batch of data into memory key-value pairs and store them in memory banks, in which each memory will dynamically update during the training process. Inspired by the non-local module, we propose to use a tri-branch way for a more efficient memory retrieval process. By training with our memory module, DCNNs can learn more holistic and discriminative features efficiently and effectively. We conduct intensive experiments on three challenging public datasets. Compared with popular segmentation networks on all three datasets, our method can achieve competitive performance while keeping relatively fewer parameters. • Using deep neural networks to extracts building footprints automatically. • Integrated memory module enables network learning to have more distinguishing feature. • The proposed memory module consumes less computation than the original module. • Implicit relation between features is established to capture discriminant features. [ABSTRACT FROM AUTHOR]

Building extraction, which is a fundamental task in the community of remote sensing image analysis, has been extensively applied in various applications related to smart cities. Due to the complicated background information in urban areas, how to extract building footprints from high-resolution aerial images is challenging. The recent achievements of deep learning have shed light on building extraction and other remote sensing domain tasks. However, the heavy consumption of computational resources and the design of the neural architectures became the biggest bottleneck of utilizing deep learning techniques to improve the performance. In this work, we developed a Neural Architecture Search (NAS) algorithm, dubbed BuildingNAS, for building extraction from high-resolution aerial images. In particular, we built an efficient candidate operation set upon Separable Factorized Residual Blocks as our cell-level search space. Different from previous NAS in semantic segmentation tasks, we employed the hierarchical search space and proposed the Single-Path Sampling strategy to eliminate excessive GPU memory comsumption in searching process. In addition, we proposed an entropy regularized objective for the optimization of architecture parameters. As the result, the larger batch size can be adopted in the whole pipeline to accelerate the searching process, and make the resulted architecture more stable and accurate. We evaluated our proposed algorithm in WHUBuilding Dataset, the derived network achieved mIoU of 86.95% with only 2.05G FLOPs and 3.10 M parameters. The comparison results demonstrate that the network discovered by our algorithm can achieve great efficiency-accuracy trade-off. • The attempt of applying neural architecture search algorithm in segmentation of aerial images. • More lightweight hierarchical search space for neural architecture search of segmentation task. • Entropy regularized objective makes the searching process more effectively. • Better trades off the accuracy and efficiency of neural networks by using neural architecture search. • Achieved mIoU of 86.85% with only 2.05G Flops and 3.10 M parameters on WHUBuilding Dataset. [ABSTRACT FROM AUTHOR]

The segmentation of high-resolution (HR) remote sensing images is very important in modern society, especially in the fields of industry, agriculture and urban modelling. Through the neural network, the machine can effectively and accurately extract the surface feature information. However, using the traditional deep learning methods requires plentiful efforts in order to find a robust architecture. In this paper, we introduce a neural network architecture search (NAS) method, called NAS-HRIS, which can automatically search neural network architecture on the dataset. The proposed method embeds a directed acyclic graph (DAG) into the search space and designs the differentiable searching process, which enables it to learn an end-to-end searching rule by using gradient descent optimization. It uses the Gumbel-Max trick to provide an efficient way when drawing samples from a non-continuous probability distribution, and it improves the efficiency of searching and reduces the memory consumption. Compared with other NAS, NAS-HRIS consumes less GPU memory without reducing the accuracy, which corresponds to a large amount of HR remote sensing imagery data. We have carried out experiments on the WHUBuilding dataset and achieved 90.44% MIoU. In order to fully demonstrate the feasibility of the method, we made a new urban Beijing Building dataset, and conducted experiments on satellite images and non-single source images, achieving better results than SegNet, U-Net and Deeplab v3+ models, while the computational complexity of our network architecture is much smaller. [ABSTRACT FROM AUTHOR]

Deforestation in the Amazon rainforest results in reduced biodiversity, habitat loss, climate change, and other destructive impacts. Hence obtaining location information on human activities is essential for scientists and governments working to protect the Amazon rainforest. We propose a novel remote sensing image classification framework that provides us with the key data needed to more effectively manage deforestation and its consequences. We introduce the attention module to separate the features which are extracted from CNN(Convolutional Neural Network) by channel, then further send the separated features to the LSTM(Long-Short Term Memory) network to predict labels sequentially. Moreover, we propose a loss function by calculating the co-occurrence matrix of all labels in the dataset and assigning different weights to each label. Experimental results on the satellite image dataset of the Amazon rainforest show that our model obtains a better F 2 score compared to other methods, which indicates that our model is effective in utilizing label dependencies to improve the performance of multi-label image classification. [ABSTRACT FROM AUTHOR]