UGCNet: An Unsupervised Semantic Segmentation Network Embedded With Geometry Consistency for Remote-Sensing Images

A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation

Semantic segmentation of high-resolution optical remote sensing images is an important but challenging task. To solve the problem that many semantic segmentation networks fail to efficiently utilize global and local context information to improve the segmentation performance, this paper proposes a semantic segmentation network based on sparse self-attention (SDANet) to model the global context dependencies. Specifically, the feature maps are first divided into four regions in spatial and channel dimensions, respectively, and the divided feature maps are rearranged to form new regions. Second, the position and channel self-attention operations are performed on the rearranged regions. Third, the feature maps are restored to the original combination and the position together with channel self-attention operations are performed again to obtain the output feature maps. Finally, semantic segmentation is completed based on the output feature maps. Extensive experiments conducted on the ISPRS Vaihingen dataset demonstrate that the proposed method is superior to self-attention-based DANet, CCNet, and other general semantic segmentation networks, such as FCN, Deeplabv3+, HRNet, etc.

Semantic segmentation has been proposed as a tool to accelerate the processing of natural history collection images. However, developing a flexible and resilient segmentation network requires an approach for adaptation which allows processing different datasets with minimal training and validation. This paper presents a cross-validation approach designed to determine whether a semantic segmentation network possesses the flexibility required for application across different collections and institutions. Consequently, the specific objectives of cross-validating the semantic segmentation network are to (a) evaluate the effectiveness of the network for segmenting image sets derived from collections different from the one in which the network was initially trained on; and (b) test the adaptability of the segmentation network for use in other types of collections. The resilience to data variations from different institutions and the portability of the network across different types of collections are required to confirm its general applicability. The proposed validation method is tested on the Natural History Museum semantic segmentation network, designed to process entomological microscope slides. The proposed semantic segmentation network is evaluated through a series of cross-validation experiments designed to test using data from two types of collections: microscope slides (from three institutions) and herbarium sheets (from seven institutions). The main contribution of this work is the method, software and ground truth sets created for this cross-validation as they can be reused in testing similar segmentation proposals in the context of digitization of natural history collections. The cross-validation of segmentation methods should be a required step in the integration of such methods into image processing workflows for natural history collections.

Abstract. Semantic instance segmentation from scenes, serving as a crucial role for 3D modelling and scene understanding. Conducting semantic segmentation before grouping instances is adopted by the existing state-of-the-art methods. However, without additional refinement, semantic errors will fully propagate into the grouping stage, resulting in low overlap with the ground truth instance. Furthermore, the proposed methods focused on indoor level scenes, which are limited when directly applied to large-scale outdoor Airborne Laser Scanning (ALS) point clouds. Numerous instances, significant object density and scale variations make ALS point clouds distinct from indoor data. In order to address the problems, we proposed a geometric characterization-aware semantic instance segmentation network, which utilized both semantic and objectness score to select potential points for grouping. And in point cloud feature learning stage, hand-craft geometry features are taken as input for geometric characterization awareness. Moreover, to address errors propagated from previous modules after grouping, we have additionally designed a per-instance refinement module. To assess semantic instance segmentation, we conducted experiments on an open-source dataset. Additionally, we performed semantic segmentation experiments to evaluate the performance of our proposed point cloud feature learning method.

Semantic segmentation is a fundamental task in remote sensing image processing. It provides pixel-level classification, which is important for many applications, such as building extraction and land use mapping. The development of convolutional neural network has considerably improved the performance of semantic segmentation. Most semantic segmentation networks are the encoder–decoder structure. Bilinear interpolation is an ordinary upsampling method in the decoder, but bilinear interpolation only considers its own features and inserts three times its own features. This over-simple and data-independent bilinear upsampling may lead to suboptimal results. In this work, we propose an upsampling method based on local relations to replace bilinear interpolation. Upsampling is performed by correlating the local relationship of feature maps of adjacent stages, which can better integrate local and global information. We also design a fusion module based on local similarity. Our proposed method with ResNet101 as the backbone of the segmentation network can improve the average <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> score and overall accuracy of the Vaihingen data set by 2.69% and 1.31%, respectively. Our proposed method also has fewer parameters and less inference time.

As remote sensing images have complex backgrounds and varying object sizes, their semantic segmentation is challenging. This study proposes a multiscale cascaded network (MSCNet) for semantic segmentation. The resolutions employed with respect to the input remote sensing images are 1, 1/2, and 1/4, which represent high, medium, and low resolutions. First, 3 backbone networks extract features with different resolutions. Then, using a multiscale attention network, the fused features are input into the dense atrous spatial pyramid pooling network to obtain multiscale information. The proposed MSCNet introduces multiscale feature extraction and attention mechanism modules suitable for remote sensing land-cover classification. Experiments are performed using the Deepglobe, Vaihingen, and Potsdam datasets; the results are compared with those of the existing classical semantic segmentation networks. The findings indicate that the mean intersection over union (mIoU) of the MSCNet is 4.73% higher than that of DeepLabv3+ with the Deepglobe datasets. For the Vaihingen datasets, the mIoU of the MSCNet is 15.3%, and 6.4% higher than those of a segmented network (SegNet), and DeepLabv3+, respectively. For the Potsdam datasets, the mIoU of the MSCNet is higher than those of a fully convolutional network, Res-U-Net, SegNet, and DeepLabv3+ by 11.18%, 5.89%, 4.78%, and 3.03%, respectively.

Image processing via convolutional neural network (CNN) has been developed rapidly for remote sensing technology. Moreover, techniques for accurately extracting building footprints from remote sensed images have attracted considerable interest owing to their wide variety of common applications, including monitoring natural disasters and urban development. Extraction of building footprints can be performed easily by semantic segmentation using U-Net-like CNN architectures. However, obtaining precise boundaries of segmentation masks remains challenging due to various impediments surrounding target objects. In this study, we propose a method to elaborate edges of buildings detected in remote sensed images to enhance the boundaries of segmentation masks. The proposed method adopts <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">holistically nested edge detection (HED)</i> , which extracts edge features at an encoder of a given architecture. In the proposed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">boundary enhancement (BE) module</i> , an extracted edge and segmentation mask are combined, sharing mutual information. To enable the proposed method efficiently to adapt to a wide variety of conditions, we design a distinctive approach adopting a HED unit and BE module, which is applicable to various semantic segmentation networks containing encoder-decoder structures. Experiments were conducted on five different datasets (DeepGlobe, Urban3D, WHU [high-resolution (HR), low-resolution (LR)], and Massachusetts). The results demonstrate that our proposed approaches improved on the performance of prior methods for extracting building footprints. Comparative experiments were conducted on various backbone architectures including U-Net, ResUNet++, TernausNet, and U-shape spatial pyramid pooling (USPP) to ensure the effectiveness of the proposed method. Based on various evaluation metrics and qualitative analysis, our results show that the proposed method achieved improved performance compared with prior methods for all datasets and backbone networks.

In view of the insufficient illumination of low-light images in semantic segmentation, there are phenomena such as low image brightness, contrast, and signal-to-noise ratio, which makes semantic segmentation of low-light images more difficult. A low-light image semantic segmentation method based on vector symbolic architectures domain adaptation network is proposed. The method first integrates the image translation network based on vector symbolic architectures and the domain adaptive semantic segmentation network. The image translation network translates normal illumination images into low-light images, reducing style differences between domains and improving the segmentation accuracy of low-light images. Then, a layered feature mapping (LFM) module is proposed in the image translation network. The LFM module can better map the multi-layer feature vectors of the semantic segmentation network encoder to the VSA space, making the translated image more similar to the low-light image, thereby improving the segmentation accuracy of the segmentation network. Finally, a cross domain rare class mixing (CDRCM) method is proposed in the domain adaptive semantic segmentation network. CDRCM obtains rare classes in the low-light domain based on the pseudo- label distribution of low-light images during domain adaptation, and biases towards these rare classes during cross-domain mixing, thereby improving the segmentation accuracy of rare classes in the low-light domain. The experimental results on Cityscapes→Dark Zurich and Cityscapes→ACDC-night indicated that the proposed method in the paper achieved improvements of 8.2 percentage points and 7.2 percentage points, respectively, in mean intersection-over-union compared to the baseline DAFormer, the experimental results show the effectiveness of the method.

Semantic segmentation plays an increasingly important role in the field of computer vision. The current semantic segmentation algorithms are mainly based on full convolutional network downsampling for feature extraction, however, the reduction of image resolution due to downsampling will inevitably lead to the loss of image information and the process is irreversible. Although features can be reused to compensate for the loss, the problem of lost pixel correlation and inaccurate segmentation results still occur. In order to solve these problems, the attention mechanism and the generative adversarial network are fused into the semantic segmentation network, and a semantic segmentation network is proposed. The attention mechanism is added to the generator and discriminator modules and trained successively, then the generator module with rich information and global information is extracted, and its output is fused with the feature graph sampled above, in order to reduce the loss of local information and complete the task of image segmentation, an interpolation method based on image edge is introduced to sample the image, which improves the bilinear interpolation edge blur. Experiments on Cityscapes dataset show that the proposed network model is effective and reliable.

Vision-based perception is an import link in driverless technology, and semantic segmentation is one of the mostly uses atrous convolution with a large amount of computation and high memory consumption to extract high-resolution feature maps. As a result, the current mainstream semantic segmentation network lacks the segmentation speed and cannot be effectively applied in driverless technology. To solve this problem, a semantic segmentation network with better real-time performance is proposed. Firstly, a lightweight convolutional neural network is used as the encoder, and stride convolution and regular convolution are used to replace the time-consuming and memory-consuming atrous convolution. Secondly, in order to obtain the feature map similar to Deeplab v3+, a new joint upsampling module, Multi-scale Feature Map Joint Pyramid Upsamping(MJPU), is proposed. By fusing multiple feature maps in the encoder, a high resolution feature map with richer semantic information is generated. Experments on the Cityscapes dataset show that, compared with the popular semantic segmentation network Deeplab V3+, the proposed network can improve the segmentation speed to 31.4 FPS/s without losing a lot of performance(mIoU of 44.03%). Therefore, the network proposed in this paper has better real-time performance and is more suitable for driverless scenes.

Linear feature extraction is crucial for special objects in semantic segmentation networks, such as slot marking and lanes. The objects with linear characteristics have global contextual information dependency. It is very difficult to capture the complete information of these objects in semantic segmentation tasks. To improve the linear feature extraction ability of the semantic segmentation network, we propose introducing the dilated convolution with vertical and horizontal kernels (DVH) into the task of feature extraction in semantic segmentation networks. Meanwhile, we figure out the outcome if we put the different vertical and horizontal kernels on different places in the semantic segmentation networks. Our networks are trained on the basis of the SS dataset, the TuSimple lane dataset and the Massachusetts Roads dataset. These datasets consist of slot marking, lanes, and road images. The research results show that our method improves the accuracy of the slot marking segmentation of the SS dataset by 2%. Compared with other state-of-the-art methods, our UnetDVH-Linear (v1) obtains better accuracy on the TuSimple Benchmark Lane Detection Challenge with a value of 97.53%. To prove the generalization of our models, road segmentation experiments were performed on aerial images. Without data argumentation, the segmentation accuracy of our model on the Massachusetts roads dataset is 95.3%. Moreover, our models perform better than other models when training with the same loss function and experimental settings. The experiment result shows that the dilated convolution with vertical and horizontal kernels will enhance the neural network on linear feature extraction.

Abstract. Unsupervised and self-supervised deep learning networks for semantic segmentation of images have made impressive progress in the last years. They can be trained without any labelled data and yet are able to effectively segment RGB images into meaningful semantic groups. In remote sensing, supplementary information, such as elevation, improves class separation by differentiating classes based to their height above ground. We take SmooSeg, a recently developed, state-of-the-art unsupervised network for semantic segmentation, and guide its training process by infusing elevation information into its projector and smoothness prior. This ensures global label consistency across the entire dataset and improves the segmentation performance, since patches of the same semantic group often exhibit similar elevation characteristics. We also extend the Conditional Random Field (CRF) to refine the low-resolution segmentation results in a post-processing step with elevation information. We introduce a second pairwise potential that encourages neighboring pixels with similar elevation to have the same label, ensuring local label consistency. Our multi-modal training strategy remains unsupervised and improves the segmentation performance on the ISPRS Potsdam-3 dataset by +4.0% in mIoU over the RGB-only SmooSeg baseline and by 4.4% when also using the multi-modal CRF post-processing. Collectively, our approach surpasses all state-of-the-art unsupervised segmentation networks that rely solely on RGB data for the Potsdam-3 dataset, highlighting the important role of elevation data in label-free segmentation for remote sensing applications.

The use of deep neural networks for semantic segmentation of RS (remote sensing) images is an important research topic in the field of remote sensing intelligent interpretation, which has significant application value in urban planning, disaster assessment, carbon estimation, and other fields. However, high-resolution RS images bring problems of large data scale, high computational complexity, diverse scales, and irregular shapes. Moreover, there may be distant spatial relationships between target objects, requiring the utilization of long-range contextual information for accurate semantic segmentation. Inspired by the powerful global modelling capability of the Swin Transformer, we propose a new RS image semantic segmentation network. Swin Transformer is used as an encoder to extract global features. To prevent the loss of local details in the encoding stage, one LKA-PM (LKA-Patch Merging) module is designed to extract local detail information by decomposing large kernel convolutions, thereby enhancing the feature representation ability of small objects. Furthermore, to decode global and local features and obtain multi-scale information, one WORC (Weighted Operation Re-parameterization Convolution) module is designed to improve the adaptability and accuracy of the model to different RS images. Finally, to preserve spatial details during decoding and reduce the problem of boundary blurring caused by occlusion in RS imagery, the Coordswin module is designed to provide coordinate information and improve the discrimination ability of similar objects. Experimental results demonstrate that our CW-SwinUNet achieves excellent segmentation performance (91.8 % F1 and 85.2 % MIoU) on the Vaihingen dataset and (93.8 % F1 and 87.9 % MIoU) on Potsdam datasets, surpassing other state-of-the-art methods. The source code of the proposed CW-SwinUNet is available at https://github.com/xmy1135/cwswin/tree/main.

As one of the most important components of urban space, an outdated inventory of road-side trees may misguide managers in the assessment and upgrade of urban environments, potentially affecting urban road quality. Therefore, automatic and accurate instance segmentation of road-side trees from urban point clouds is an important task in urban ecology research. However, previous works show under- or over-segmentation effects for road-side trees due to overlapping, irregular shapes and incompleteness. In this paper, a deep learning framework that combines semantic and instance segmentation is proposed to extract single road-side trees from vehicle-mounted mobile laser scanning (MLS) point clouds. In the semantic segmentation stage, the ground points are filtered to reduce the processing time. Subsequently, a graph-based semantic segmentation network is developed to segment road-side tree points from the raw MLS point clouds. For the individual tree segmentation stage, a novel joint instance and semantic segmentation network is adopted to detect instance-level roadside trees. Two complex Chinese urban point cloud scenes are used to evaluate the individual urban tree segmentation performance of the proposed method. The proposed method accurately extract approximately 90% of the road-side trees and achieve better segmentation results than existing published methods in both two urban MLS point clouds. Living Vegetation Volume (LVV) calculation can benefit from individual tree segmentation. The proposed method provides a promising solution for ecological construction based on the LVV calculation of urban roads.

The semantic segmentation of remote sensing images faces two major challenges: high inter-class similarity and interference from ubiquitous shadows. In order to address these issues, we develop a novel edge loss reinforced semantic segmentation network (ERN) that leverages the spatial boundary context to reduce the semantic ambiguity. The main contributions of this paper are as follows: (1) we propose a novel end-to-end semantic segmentation network for remote sensing, which involves multiple weighted edge supervisions to retain spatial boundary information; (2) the main representations of the network are shared between the edge loss reinforced structures and semantic segmentation, which means that the ERN simultaneously achieves semantic segmentation and edge detection without significantly increasing the model complexity; and (3) we explore and discuss different ERN schemes to guide the design of future networks. Extensive experimental results on two remote sensing datasets demonstrate the effectiveness of our approach both in quantitative and qualitative evaluation. Specifically, the semantic segmentation performance in shadow-affected regions is significantly improved.