Semantic Segmentation Method Research Articles

Advancing high-resolution remote sensing: a compact and powerful approach to semantic segmentation

ABSTRACT Deep learning (DL)-based approaches are notable for their ability to establish feature associations without relying on physical constraints, unlike traditional strategies that are complex and dependent on expert experience. However, three main challenges hinder the versatility of semantic segmentation models. First, the targets in these images are dense and exist at varying spatial scales, which imposes higher demands on the model for accurate segmentation across scales. Second, the segmentation of small targets in the images is often overlooked, leading to a compromise between fine segmentation and model efficiency. Lastly, the data-intensive nature of remote sensing images and the resource-intensive operations of large-scale networks impose significant communication and computation burdens on edge devices, which may not have sufficient resources to handle them effectively. To address these challenges, this paper proposes a lightweight semantic segmentation method for remote sensing images to achieve high-precision segmentation for multi-scale targets while maintaining low computational complexity. The main components include: (1) embedding the inverted residual block structure to minimize the number of model parameters and computational costs; (2) introducing the parallel irregular space pyramid pooling module to efficiently aggregate multi-scale contextual information for fine-grained recognition of small targets; and (3) embedding transfer learning into the encoder-decoder structure to speed up the convergence rate and improve multi-scale feature fusion capability, thereby reducing semantic information loss. The proposed lightweight method has been extensively tested on real-world high-resolution remote sensing datasets. It achieved PA, MPA, MIoU, and FWIoU scores of 87.90%, 75.76%, 66.29%, and 78.81% on the Vaihingen dataset; 87.03%, 85.31%, 74.85%, and 77.54% on the Potsdam dataset; and 95.37%, 83.33%, 75.70%, and 91.31% on the Aeroscapes dataset. Compared to other popular semantic segmentation models, the proposed method achieved the highest values in all four evaluation indicators, demonstrating its effectiveness and superiority.

Multi-Scale Classification and Contrastive Regularization: Weakly Supervised Large-Scale 3D Point Cloud Semantic Segmentation

With the proliferation of large-scale 3D point cloud datasets, the high cost of per-point annotation has spurred the development of weakly supervised semantic segmentation methods. Current popular research mainly focuses on single-scale classification, which fails to address the significant feature scale differences between background and objects in large scenes. Therefore, we propose MCCR (Multi-scale Classification and Contrastive Regularization), an end-to-end semantic segmentation framework for large-scale 3D scenes under weak supervision. MCCR first aggregates features and applies random downsampling to the input data. Then, it captures the local features of a random point based on multi-layer features and the input coordinates. These features are then fed into the network to obtain the initial and final prediction results, and MCCR iteratively trains the model using strategies such as contrastive learning. Notably, MCCR combines multi-scale classification with contrastive regularization to fully exploit multi-scale features and weakly labeled information. We investigate both point-level and local contrastive regularization to leverage point cloud augmentor and local semantic information and introduce a Decoupling Layer to guide the loss optimization in different spaces. Results on three popular large-scale datasets, S3DIS, SemanticKITTI and SensatUrban, demonstrate that our model achieves state-of-the-art (SOTA) performance on large-scale outdoor datasets with only 0.1% labeled points for supervision, while maintaining strong performance on indoor datasets.

Dynahead-YOLO-Otsu: an efficient DCNN-based landslide semantic segmentation method using remote sensing images

Recent advancements in deep convolutional neural networks (DCNNs) have significantly improved landslides identification using remote sensing images. Pixel-wise semantic segmentation (PSS) and object-oriented detection (OOD) are two dominant approaches, wherein PSS are better as providing detailed delineation of landslide shapes. However, PSS are limited by the difficulty in labelling training data and low segmentation speed compared to OOD. In this paper, we propose an efficient DCNN-based landslide semantic segmentation method, the so-called Dynahead-YOLO-Otsu, to perform a PSS based on the OOD results. This is achieved by locating potential landslide regions in advance using the ODD-based Dynahead-YOLO model, which enhances the capacity for detecting landslides with variable proportions and complex background in the images. The preliminary results are then processed using the Otsu binarization algorithm to cluster pixels belonging to landslides from the images of potential regions for semantic segmentation. To validate the performance, we tested the proposed method using an open-source dataset containing 950 landslide images. We compared the results with three up-to-date DCNN-and PSS- based approaches, namely DeepLab v3+, PSPnet, and Unet. Results demonstrate that the proposed method achieves comparable Recall (71.80%) and F1 scores (75.80%), with an average improvement of 22% and 16% in Precision and IoU, respectively.

MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation.

Noisy labels, inevitably existing in pseudo-segmentation labels generated from weak object-level annotations, severely hamper model optimization for semantic segmentation. Previous works often rely on massive handcrafted losses and carefully tuned hyperparameters to resist noise, suffering poor generalization capability and high model complexity. Inspired by recent advances in meta-learning, we argue that rather than struggling to tolerate noise hidden behind clean labels passively, a more feasible solution would be to find out the noisy regions actively, so as to simply ignore them during model optimization. With this in mind, this work presents a novel meta-learning-based semantic segmentation method, MetaSeg, that comprises a primary content-aware meta-net (CAM-Net) to serve as a noise indicator for an arbitrary segmentation model counterpart. Specifically, CAM-Net learns to generate pixel-wise weights to suppress noisy regions with incorrect pseudo-labels while highlighting clean ones by exploiting hybrid strengthened features from image content, providing straightforward and reliable guidance for optimizing the segmentation model. Moreover, to break the barrier of time-consuming training when applying meta-learning to common large segmentation models, we further present a new decoupled training strategy that optimizes different model layers in a divide-and-conquer manner. Extensive experiments on object, medical, remote sensing, and human segmentation show that our method achieves superior performance, approaching that of fully supervised settings, which paves a new promising way for omni-supervised semantic segmentation.

Semantic Segmentation of Point Cloud Scene via Multi-Scale Feature Aggregation and Adaptive Fusion

Point cloud semantic segmentation is a key step in 3D scene understanding and analysis. In recent years, deep learning–based point cloud semantic segmentation methods have received extensive attention from researchers. Multi-scale neighborhood feature learning methods are suitable for inhomogeneous density point clouds, but different scale branching feature learning increases the computational complexity and makes it difficult to accurately fuse different scale features to express local information. In this study, a point cloud semantic segmentation network based on RandLA-Net with multi-scale local feature aggregation and adaptive fusion is proposed. The designed structure can reduce computational complexity and accurately express local features. The mean intersection-over-union is improved by 1.1% on the SemanticKITTI data set with an inference speed of nine frames per second, while the mean intersection-over-union is improved by 0.9% on the S3DIS data set, compared with RandLA-Net. We also conduct ablation studies to validate the effectiveness of the proposed key structure.

ASCEND-UNet: An Improved UNet Configuration Optimized for Rural Settlements Mapping.

Different types of rural settlement agglomerations have been formed and mixed in space during the rural revitalization strategy implementation in China. Discriminating them from remote sensing images is of great significance for rural land planning and living environment improvement. Currently, there is a lack of automatic methods for obtaining information on rural settlement differentiation. In this paper, an improved encoder-decoder network structure, ASCEND-UNet, was designed based on the original UNet. It was implemented to segment and classify dispersed and clustered rural settlement buildings from high-resolution satellite images. The ASCEND-UNet model incorporated three components: firstly, the atrous spatial pyramid pooling (ASPP) multi-scale feature fusion module was added into the encoder, then the spatial and channel squeeze and excitation (scSE) block was embedded at the skip connection; thirdly, the hybrid dilated convolution (HDC) block was utilized in the decoder. In our proposed framework, the ASPP and HDC were used as multiple dilated convolution blocks to expand the receptive field by introducing a series of dilated rate convolutions. The scSE is an attention mechanism block focusing on features both in the spatial and channel dimension. A series of model comparisons and accuracy assessments with the original UNet, PSPNet, DeepLabV3+, and SegNet verified the effectiveness of our proposed model. Compared with the original UNet model, ASCEND-UNet achieved improvements of 4.67%, 2.80%, 3.73%, and 6.28% in precision, recall, F1-score and MIoU, respectively. The contributions of HDC, ASPP, and scSE modules were discussed in ablation experiments. Our proposed model obtained more accurate and stable results by integrating multiple dilated convolution blocks with an attention mechanism. This novel model enriches the automatic methods for semantic segmentation of different rural settlements from remote sensing images.

MATNet: multiattention Transformer network for cropland semantic segmentation in remote sensing images

ABSTRACT Remote sensing image semantic segmentation methods have become the main approach for extracting cropland information. However, in the mountainous regions of southwestern China, croplands exhibit narrow and fragmented shapes, as well as complex planting patterns, making it difficult for traditional semantic segmentation methods to accurately delineate fine-grained cropland boundaries. To address these challenges, a multiattention Transformer network named MATNet is proposed in this paper, for fine-grained extraction of cropland at the parcel level in complex scenes. MATNet built upon the fusion of CNN encoder and Transformer decoder. In the encoder, spatial and channel reconstruction units are introduced, reducing information redundancy in the convolutional layers. The Transformer decoder incorporates multiple attention mechanisms, this design feature enhances the attention window's perception of local content and improves the model's ability to extract features from fine-grained cropland parcels through optimized computationnal al location. Taking the experimental results of the Dali cropland dataset as an illustration, MATNet achieved the highest values across five evaluation metrics, including mIoU. Specifically, the Recall, F1, and mIoU scores were 94.68%, 94.69%, and 89.92%, respectively. Compared with six other advanced models, MATNet consistently performed best in terms of extracting fine-grained cropland parcels.

A Segment Anything Model based weakly supervised learning method for crop mapping using Sentinel-2 time series images

Automatic crop mapping is essential for various agricultural applications. Although fully convolutional networks (FCNs) have shown effectiveness in crop mapping, they rely on labor-intensive pixel-level annotations. Weakly supervised semantic segmentation (WSSS) methods offer a solution by enabling pixel-level segmentation with less costly annotations, such as point, bounding box (bbox), and image-level annotations. However, these weak annotations often lack complete object information, leading to reduced accuracy. Moreover, there is limited exploration of WSSS methods in medium-resolution satellite imagery, such as Sentinel-2. Therefore, this study proposes SAMWS, a WSSS method based on the Segment Anything Model (SAM) for crop mapping using Sentinel-2 time series images. Leveraging SAM, our method can generate high-quality pseudo labels and accommodate various weak annotations without extensive adjustments. SAMWS comprises three stages: 1) finetuning SAM with adapters; 2) generating pseudo labels using weak annotations and finetuned SAM; and 3) training a segmentation network using pseudo labels for crop mapping. Experiments conducted on PASTIS and Munich datasets demonstrate the superiority of our approach. After SAM was finetuned with adapters, the F1-scores for parcel segmentation using point and bbox prompts increased by 75.0 % and 14.4 %, respectively, reaching 0.880 and 0.931. Additionally, our method achieves classification results closest to fully supervised learning when using point, bbox, and image-level annotations, with F1-scores of 0.810, 0.817, and 0.779, respectively. Our approach offers valuable insights into leveraging foundation models in the remote sensing domain and contains significant potential for crop monitoring. The relevant code will be made publicly available at https://github.com/Nick0317Sun/SAMWS.

BMSeNet: Multiscale Context Pyramid Pooling and Spatial Detail Enhancement Network for Real-Time Semantic Segmentation.

Most real-time semantic segmentation networks use shallow architectures to achieve fast inference speeds. This approach, however, limits a network's receptive field. Concurrently, feature information extraction is restricted to a single scale, which reduces the network's ability to generalize and maintain robustness. Furthermore, loss of image spatial details negatively impacts segmentation accuracy. To address these limitations, this paper proposes a Multiscale Context Pyramid Pooling and Spatial Detail Enhancement Network (BMSeNet). First, to address the limitation of singular semantic feature scales, a Multiscale Context Pyramid Pooling Module (MSCPPM) is introduced. By leveraging various pooling operations, this module efficiently enlarges the receptive field and better aggregates multiscale contextual information. Moreover, a Spatial Detail Enhancement Module (SDEM) is designed, to effectively compensate for lost spatial detail information and significantly enhance the perception of spatial details. Finally, a Bilateral Attention Fusion Module (BAFM) is proposed. This module leverages pixel positional correlations to guide the network in assigning appropriate weights to the features extracted from the two branches, effectively merging the feature information of both branches. Extensive experiments were conducted on the Cityscapes and CamVid datasets. Experimental results show that the proposed BMSeNet achieves a good balance between inference speed and segmentation accuracy, outperforming some state-of-the-art real-time semantic segmentation methods.

Point cloud semantic segmentation of grotto scenes using the knowledge-guided deep learning method

ABSTRACT In recent years, the deep learning-based semantic segmentation for point clouds has demonstrated remarkable capabilities in processing 3D urban scenes for applications such as three-dimensional reconstruction, semantic modeling, and augmented reality. However, research on grottoes scenes is very limited. It is currently unclear how existing neural architectures for point cloud semantic segmentation perform in grotto scenes, and how to effectively incorporate the unique characteristics of grotto scenes to enhance the performance of deep neural networks. This study proposed a method for point cloud semantic segmentation of grotto scenes, combining knowledge with deep learning approaches. The method adopted knowledge to guide the creation of benchmark datasets, the design of a neural network called GSS-Net, and the correction of segmentation errors in the results of deep learning. The results show that the proposed method outperforms four existing mainstream models without the correction of segmentation results. Moreover, a set of ablation studies verified the effectiveness of each proposed module. This method not only improves the accuracy of point cloud semantic segmentation in grotto scenes but also enhances the interpretability of network designs. It provides new insights into the application of knowledge-guided deep learning models in grotto scenes.

A Self-Supervised Few-Shot Semantic Segmentation Method Based on Multi-Task Learning and Dense Attention Computation.

Nowadays, autonomous driving technology has become widely prevalent. The intelligent vehicles have been equipped with various sensors (e.g., vision sensors, LiDAR, depth cameras etc.). Among them, the vision systems with tailored semantic segmentation and perception algorithms play critical roles in scene understanding. However, the traditional supervised semantic segmentation needs a large number of pixel-level manual annotations to complete model training. Although few-shot methods reduce the annotation work to some extent, they are still labor intensive. In this paper, a self-supervised few-shot semantic segmentation method based on Multi-task Learning and Dense Attention Computation (dubbed MLDAC) is proposed. The salient part of an image is split into two parts; one of them serves as the support mask for few-shot segmentation, while cross-entropy losses are calculated between the other part and the entire region with the predicted results separately as multi-task learning so as to improve the model's generalization ability. Swin Transformer is used as our backbone to extract feature maps at different scales. These feature maps are then input to multiple levels of dense attention computation blocks to enhance pixel-level correspondence. The final prediction results are obtained through inter-scale mixing and feature skip connection. The experimental results indicate that MLDAC obtains 55.1% and 26.8% one-shot mIoU self-supervised few-shot segmentation on the PASCAL-5i and COCO-20i datasets, respectively. In addition, it achieves 78.1% on the FSS-1000 few-shot dataset, proving its efficacy.

Extraction of Sunspots from Chinese Sunspot Drawings Based on Semisupervised Learning

China has six observing stations, providing over 52,000 handwritten sunspot drawings from 1947–2016. The observing stations are the Purple Mountain Astronomical Observatory (PMO), Yunnan Astronomical Observatory (YNAO), Qingdao Observatory Station (QDOS), Sheshan Observatory Station (SSOS), Beijing Planetarium (BJP), and Nanjing University (NJU). In this paper, we propose a new cotraining semisupervised learning method combining a semantic segmentation method named dynamic mutual training (DMT) boundary-guided semantic segmentation (BGSeg), i.e., DMT_BGSeg, which makes full use of the labeled data from PMO and the unlabeled data from the other five stations to detect and segment sunspot components in all sunspot drawings of the six Chinese stations. The sunspot is detected and segmented. Additionally, each sunspot is split into four types of components: pore, spot, umbra, and hole. The testing results show the mIoU values of PMO, YNAO, BJP, NJU, QDOS and SSOS are 85.29, 72.65, 73.82, 64.28, 62.26, and 60.07, respectively. The results of the comparison also show that DMT_BGSeg is effective in detecting and segmenting sunspots in Chinese sunspot drawings. The numbers and areas of sunspot components are measured separately. All of the detailed data are publicly shared on China-VO, which will advance the comprehensive augmentation of the global historical sunspot database and further the understanding of the long-term solar activity cycle and solar dynamo.

Semantic segmentation method for micro-cracks in silicon nitride ceramic bearing balls based on coupling of edge channel enhancement and weighted gated attention mechanism in EMU-Net+

In addressing the issues of blurred microcrack edge gradients and mutual interference among various types of microcracks in the semantic segmentation of microcracks in silicon nitride bearing balls. Based on coupling edge channel enhancement and a weighted gated attention mechanism within the EMU-Net + framework method is proposed. The Unet + function matrix is constructed with long-short connection structures, incorporating feature fusion across different layers to obtain a larger receptive field. The edge channel enhancement and weighted gated attention mechanism are established, feeding back features segmented at different scales to the higher level, enhancing the contrast between features and the background, achieving finer segmentation of microcrack mask images. Compared to the baseline Unet model, segmentation metrics including Miou, Mpa, Precision, and Recall on the microcrack dataset are improved by 6.73 %, 3.1 %, 5 %, and 3.41 %, respectively. The average intersection and merger ratios of three different microcrack types all exceed 80 %.

Semantic segmentation algorithm for video from UAV based on adaptive keyframe scheduling via similarity measurement

Abstract Unmanned aerial vehicle (UAV) videos exhibit complex object motion features and significant differences between frame features. To solve the problems of feature information loss and drastic accuracy decline in applying the video semantic segmentation method based on the fixed-period update strategy of keyframes, a keyframe recognition method based on similarity measurement is proposed, forming a video semantic segmentation algorithm based on adaptive keyframe scheduling. one keyframe recognition method based on pixel similarity measurement is established by modeling the similarity relationship between low-level pixels in adjacent frames. Meanwhile, the other keyframe recognition method based on feature similarity measurement is established by constructing a shallow Siamese network to measure the similarity relationship between features of frames. Then a discriminative network is constructed based on the obtained similarity of inter frames, and the segmentation process is accelerated by reusing features of keyframes through the optical flow network. Thereby a video semantic segmentation method for UAV based on adaptive keyframe strategy is established. The effectiveness of the proposed video semantic segmentation algorithm is verified on UAVid dataset. The results demonstrated that the speed of the proposed algorithm reaches 53.2 FPS and 54.5 FPS on the premise that the mean intersection over union is higher than 40% (this value is compared with the segmentation accuracy in the balanced mode when the similarity threshold is 0.76 and 0.88, respectively), which is 18.5 FPS and 19.8 FPS higher than the PSPNet image semantic segmentation algorithm. In addition, analysis of experiment results shows that the pixel-similarity-based keyframe recognition is suitable for high-precision video semantic segmentation scenes that need to improve segmentation efficiency, and the feature-similarity-based keyframe recognition is more suitable for high real-time video semantic segmentation tasks that require a small decrease in overall algorithm accuracy. 
In a word, the proposed video semantic segmentation algorithm based on adaptive keyframe scheduling via similarity measurement can improve segmentation speed while ensuring segmentation accuracy and stability.

A Novel Mamba Architecture with a Semantic Transformer for Efficient Real-Time Remote Sensing Semantic Segmentation

Real-time remote sensing segmentation technology is crucial for unmanned aerial vehicles (UAVs) in battlefield surveillance, land characterization observation, earthquake disaster assessment, etc., and can significantly enhance the application value of UAVs in military and civilian fields. To realize this potential, it is essential to develop real-time semantic segmentation methods that can be applied to resource-limited platforms, such as edge devices. The majority of mainstream real-time semantic segmentation methods rely on convolutional neural networks (CNNs) and transformers. However, CNNs cannot effectively capture long-range dependencies, while transformers have high computational complexity. This paper proposes a novel remote sensing Mamba architecture for real-time segmentation tasks in remote sensing, named RTMamba. Specifically, the backbone utilizes a Visual State-Space (VSS) block to extract deep features and maintains linear computational complexity, thereby capturing long-range contextual information. Additionally, a novel Inverted Triangle Pyramid Pooling (ITP) module is incorporated into the decoder. The ITP module can effectively filter redundant feature information and enhance the perception of objects and their boundaries in remote sensing images. Extensive experiments were conducted on three challenging aerial remote sensing segmentation benchmarks, including Vaihingen, Potsdam, and LoveDA. The results show that RTMamba achieves competitive performance advantages in terms of segmentation accuracy and inference speed compared to state-of-the-art CNN and transformer methods. To further validate the deployment potential of the model on embedded devices with limited resources, such as UAVs, we conducted tests on the Jetson AGX Orin edge device. The experimental results demonstrate that RTMamba achieves impressive real-time segmentation performance.

Weighted Intersection over Union (wIoU) for evaluating image segmentation

In recent years, many semantic segmentation methods have been proposed to predict label of pixels in the scene. In general, we measure area prediction errors or boundary prediction errors for comparing methods. However, there is no intuitive evaluation metric that evaluates both aspects. In this work, we propose a new evaluation measure called weighted Intersection over Union (wIoU) for semantic segmentation. First, it builds a weight map generated from a boundary distance map, allowing weighted evaluation for each pixel based on a boundary importance factor. The proposed wIoU can evaluate both contour and region by setting a boundary importance factor. We validated the effectiveness of wIoU on a dataset of 33 scenes and demonstrated its flexibility. Using the proposed metric, we expect more flexible and intuitive evaluation in semantic segmentation field are possible.

TAJ-Net: a two-stage clustered cell segmentation network with adaptive joint learning of spatial and spectral information.

Pulmonary adenocarcinoma is the primary cause of cancer-related death worldwide and pathological diagnosis is the "golden standard" based on the regional distribution of cells. Thus, regional cell segmentation is a key step while it is challenging due to the following reasons: 1) It is hard for pure semantic and instance segmentation methods to obtain a high-quality regional cell segmentation result; 2) Since the spatial appearances of pulmonary cells are very similar which even confuse pathologists, annotation errors are usually inevitable. Considering these challenges, we propose a two-stage 3D adaptive joint training framework (TAJ-Net) to segment-then-classify cells with extra spectral information as the supplementary information of spatial information. Firstly, we propose to leverage a few-shot method with limited data for cell mask acquisition to avoid the disturbance of cluttered backgrounds. Secondly, we introduce an adaptive joint training strategy to remove noisy samples through two 3D networks and one 1D network for cell type classification rather than segmentation. Subsequently, we propose a patch mapping method to map classification results to the original images to obtain regional segmentation results. In order to verify the effectiveness of TAJ-Net, we build two 3D hyperspectral datasets, i.e., pulmonary adenocarcinoma (3,660 images) and thyroid carcinoma (4623 images) with 40 bands. The first dataset will be released for further research. Experiments show that TAJ-Net achieves much better performance in clustered cell segmentation, and it can regionally segment different kinds of cells with high overlap and blurred edges, which is a difficult task for the state-of-the-art methods. Compared to 2D models, the hyperspectral image-based 3D model reports a significant improvement of up to 11.5% in terms of the Dice similarity coefficient in the pulmonary adenocarcinoma dataset.

Semantic segmentation of point clouds of ancient buildings based on weak supervision

Semantic segmentation of point clouds of ancient buildings plays an important role in Historical Building Information Modelling (HBIM). As the annotation task of point cloud of ancient architecture is characterised by strong professionalism and large workload, which greatly restricts the application of point cloud semantic segmentation technology in the field of ancient architecture, therefore, this paper launches a research on the semantic segmentation method of point cloud of ancient architecture based on weak supervision. Aiming at the problem of small differences between classes of ancient architectural components, this paper introduces a self-attention mechanism, which can effectively distinguish similar components in the neighbourhood. Moreover, this paper explores the insufficiency of positional encoding in baseline and constructs a high-precision point cloud semantic segmentation network model for ancient buildings—Semantic Query Network based on Dual Local Attention (SQN-DLA). Using only 0.1% of the annotations in our homemade dataset and the Architectural Cultural Heritage (ArCH) dataset, the mean Intersection over Union (mIoU) reaches 66.02% and 58.03%, respectively, which is an improvement of 3.51% and 3.91%, respectively, compared to the baseline.

Active Bidirectional Self-Training Network for Cross-Domain Segmentation in Remote-Sensing Images

Semantic segmentation with cross-domain adaptation in remote-sensing images (RSIs) is crucial and mitigates the expense of manually labeling target data. However, the performance of existing unsupervised domain adaptation (UDA) methods is still significantly impacted by domain bias, leading to a considerable gap compared to supervised trained models. To address this, our work focuses on semi-supervised domain adaptation, selecting a small subset of target annotations through active learning (AL) that maximize information to improve domain adaptation. Overall, we propose a novel active bidirectional self-training network (ABSNet) for cross-domain semantic segmentation in RSIs. ABSNet consists of two sub-stages: a multi-prototype active region selection (MARS) stage and a source-weighted class-balanced self-training (SCBS) stage. The MARS approach captures the diversity in labeled source data by introducing multi-prototype density estimation based on Gaussian mixture models. We then measure inter-domain similarity to select complementary and representative target samples. Through fine-tuning with the selected active samples, we propose an enhanced self-training strategy SCBS, designed for weighted training on source data, aiming to avoid the negative effects of interfering samples. We conduct extensive experiments on the LoveDA and ISPRS datasets to validate the superiority of our method over existing state-of-the-art domain-adaptive semantic segmentation methods.

Deep learning in autonomous driving: Advantages, limitations, and innovative solutions

With the rapid development of autonomous driving technology, deep learning has become a core driver for innovation in testing autonomous driving scenarios. This review paper delves into the critical role of deep learning in autonomous driving technology. The paper will describe how deep learning is at the center of driving innovation. The paper thoroughly explores the application of deep learning in obstacle detection, scene classification and understanding, and image segmentation, emphasizing the significant benefits in perception and decision-making while pointing out the challenges and innovative solutions adopted. The innovative solutions section proposes multimodal fusion and joint learning, new methods for 3D semantic segmentation, etc., aiming to improve image segmentation's accuracy and generalization ability. Overall, deep learning has great potential in automated driving technology, and by innovating and solving challenges, it will advance the system and provide reliable, intelligent, and efficient solutions for future transportation systems.