Boundary Guided Context Aggregation for Semantic Segmentation

Ma, Haoxiang; Yang, Hongyu; Huang, Di

doi:10.48550/arxiv.2110.14587

Cited by 7 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through CAAM, the model not only identifies fine structures and patterns within the image more accurately but also maintains high performance in challenging scenarios [43]. The introduction of this approach highlights the paramount importance of intelligently aggregating contextual information in image processing.…”

Section: Context Aggregation Attention Mechanismmentioning

confidence: 99%

Revolutionizing Target Detection in Intelligent Traffic Systems: YOLOv8-SnakeVision

Liu,

Lin

2023

Electronics

View full text Add to dashboard Cite

Intelligent traffic systems represent one of the crucial domains in today’s world, aiming to enhance traffic management efficiency and road safety. However, current intelligent traffic systems still face various challenges, particularly in the realm of target detection. These challenges include adapting to complex traffic scenarios and the lack of precise detection for multiple objects. To address these issues, we propose an innovative approach known as YOLOv8-SnakeVision. This method introduces Dynamic Snake Convolution, Context Aggregation Attention Mechanisms, and the Wise-IoU strategy within the YOLOv8 framework to enhance target detection performance. Dynamic Snake Convolution assists in accurately capturing complex object shapes and features, especially in cases of target occlusion or overlap. The Context Aggregation Attention Mechanisms allow the model to better focus on critical image regions and effectively integrate information, thus improving its ability to recognize obscured targets, small objects, and complex patterns. The Wise-IoU strategy combines dynamic non-monotonic focusing mechanisms, aiming to more precisely regress target bounding boxes, particularly for low-quality examples. We validate our approach on the BDD100K and NEXET datasets. Experimental results demonstrate that YOLOv8-SnakeVision excels in various complex road traffic scenarios. It not only enhances small object detection but also strengthens the ability to recognize multiple targets. This innovative method provides robust support for the development of intelligent traffic systems and holds the promise of achieving further breakthroughs in future applications.

show abstract

Section: Context Aggregation Attention Mechanismmentioning

confidence: 99%

Revolutionizing Target Detection in Intelligent Traffic Systems: YOLOv8-SnakeVision

Liu,

Lin

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…The self-attention mechanism works by calculating the relative importance and establishing an association between one pixel and all the other pixels, rather than just relying on elements in adjacent positions, which aids in effectively capturing the long-term dependencies between pixels [50]. The multihead attention mechanism is developed on the basis of self-attention, which enhances the expressiveness and generalization ability of the model [51]. The channel attention mechanism operates by assessing the importance of each channel, and it generates more representative features.…”

Section: Feature Fusion Module Based On Attention Mechanismmentioning

confidence: 99%

“…Considering the advantages of the attention mechanism, and inspired by the multihead feed-forward transfer attention module [29] and the boundary-guided context aggregation module [51]-which utilizes the multihead attention mechanism to fuse the feature maps of different convolution layers-we have designed the feature fusion module based on the attention mechanism (FFMAM) to promote the mutual guidance of two branches, integrate the features extracted, and explore the relationship between the channels. As the left of Figure 5 shows, the feature tensor X ∈ R C×H×W , derived from the convolution branch, is used to generate the key vector (Key) and the value vector (Value) through different reshape modes; meanwhile, the feature tensor Y ∈ R C×H×W , acquired from the Swin transformer branch, is employed for generating the query vector (Query).…”

Section: Feature Fusion Module Based On Attention Mechanismmentioning

confidence: 99%

A Hybrid Algorithm with Swin Transformer and Convolution for Cloud Detection

Gong,

Long,

Yin

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Cloud detection is critical in remote sensing image processing, and convolutional neural networks (CNNs) have significantly advanced this field. However, traditional CNNs primarily focus on extracting local features, which can be challenging for cloud detection due to the variability in the size, shape, and boundaries of clouds. To address this limitation, we propose a hybrid Swin transformer–CNN cloud detection (STCCD) network that combines the strengths of both architectures. The STCCD network employs a novel dual-stream encoder that integrates Swin transformer and CNN blocks. Swin transformers can capture global context features more effectively than traditional CNNs, while CNNs excel at extracting local features. The two streams are fused via a fusion coupling module (FCM) to produce a richer representation of the input image. To further enhance the network’s ability in extracting cloud features, we incorporate a feature fusion module based on the attention mechanism (FFMAM) and an aggregation multiscale feature module (AMSFM). The FFMAM selectively merges global and local features based on their importance, while the AMSFM aggregates feature maps from different spatial scales to obtain a more comprehensive representation of the cloud mask. We evaluated the STCCD network on three challenging cloud detection datasets (GF1-WHU, SPARCS, and AIR-CD), as well as the L8-Biome dataset to assess its generalization capability. The results show that the STCCD network outperformed other state-of-the-art methods on all datasets. Notably, the STCCD model, trained on only four bands (visible and near-infrared) of the GF1-WHU dataset, outperformed the official Landsat-8 Fmask algorithm in the L8-Biome dataset, which uses additional bands (shortwave infrared, cirrus, and thermal).

show abstract

“…Liang et al (2021) enabled the network to comprehensively capture local and global features of indoor building structure point clouds through a newly designed multi-level hierarchical feature decoding method, which enables automatic and efficient semantic segmentation. Ma et al (2021) proposed a boundary-guided contextual aggregation network by designing boundary extractors for accurate boundary detection. This contextual aggregation approach helps to capture the long-range correlation between pixels in the boundary region and pixels inside the object to improve intra-class consistency.…”

Section: Related Workmentioning

confidence: 99%

BFFNet: a bidirectional feature fusion network for semantic segmentation of remote sensing objects

Hou

Ren

et al. 2023

IJICC

View full text Add to dashboard Cite

PurposeHigh-resolution remote sensing images possess a wealth of semantic information. However, these images often contain objects of different sizes and distributions, which make the semantic segmentation task challenging. In this paper, a bidirectional feature fusion network (BFFNet) is designed to address this challenge, which aims at increasing the accurate recognition of surface objects in order to effectively classify special features.Design/methodology/approachThere are two main crucial elements in BFFNet. Firstly, the mean-weighted module (MWM) is used to obtain the key features in the main network. Secondly, the proposed polarization enhanced branch network performs feature extraction simultaneously with the main network to obtain different feature information. The authors then fuse these two features in both directions while applying a cross-entropy loss function to monitor the network training process. Finally, BFFNet is validated on two publicly available datasets, Potsdam and Vaihingen.FindingsIn this paper, a quantitative analysis method is used to illustrate that the proposed network achieves superior performance of 2–6%, respectively, compared to other mainstream segmentation networks from experimental results on two datasets. Complete ablation experiments are also conducted to demonstrate the effectiveness of the elements in the network. In summary, BFFNet has proven to be effective in achieving accurate identification of small objects and in reducing the effect of shadows on the segmentation process.Originality/valueThe originality of the paper is the proposal of a BFFNet based on multi-scale and multi-attention strategies to improve the ability to accurately segment high-resolution and complex remote sensing images, especially for small objects and shadow-obscured objects.

show abstract

Boundary Guided Context Aggregation for Semantic Segmentation

Cited by 7 publications

References 30 publications

Revolutionizing Target Detection in Intelligent Traffic Systems: YOLOv8-SnakeVision

Revolutionizing Target Detection in Intelligent Traffic Systems: YOLOv8-SnakeVision

A Hybrid Algorithm with Swin Transformer and Convolution for Cloud Detection

BFFNet: a bidirectional feature fusion network for semantic segmentation of remote sensing objects

Contact Info

Product

Resources

About