Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Yuanhua Pei"'
Publikováno v:
IET Computer Vision, Vol 17, Iss 6, Pp 652-662 (2023)
Abstract Semantic segmentation is a fundamental technology for autonomous driving. It has a high demand for inference speed and accuracy. However, a good trade‐off between accuracy and latency is yet not present in existing semantic segmentation ap
Externí odkaz:
https://doaj.org/article/6532a215fd3745358be5b9fac30024f1
Publikováno v:
Complex & Intelligent Systems, Vol 9, Iss 6, Pp 7213-7225 (2023)
Abstract For the purpose of object detection, numerous key points based methods have been suggested. To alleviate the imbalance problem that some objects may be missing when a single-center-point based network is used for object detection, we propose
Externí odkaz:
https://doaj.org/article/25f8bf2b001c4eeb80171805b8848c28
Publikováno v:
Complex & Intelligent Systems, Vol 9, Iss 6, Pp 7155-7170 (2023)
Abstract The semantic information can ensure better pixel classification, and the spatial information of the low-level feature map can ensure the detailed location of the pixels. However, this part of spatial information is often ignored in capturing
Externí odkaz:
https://doaj.org/article/ced21c7b8d2c47d89ca91d915254dba1
Publikováno v:
Complex & Intelligent Systems, Vol 9, Iss 6, Pp 6177-6190 (2023)
Abstract The traditional complete dual-branch structure is effective for semantic segmentation tasks. However, it is redundant in some sense. Moreover, the simple additive fusion of the features from the two branches may not achieve the satisfactory
Externí odkaz:
https://doaj.org/article/9774a30c4aaa4d3cba7e43c2d190c25a
Publikováno v:
Mathematics, Vol 11, Iss 12, p 2655 (2023)
Numerous deep learning-based object detection methods have achieved excellent performance. However, the performance on small-size object detection and positive and negative sample imbalance problems is not satisfactory. We propose a multi-scale featu
Externí odkaz:
https://doaj.org/article/73d83101bbb544c8b996843c8ff486b4
Publikováno v:
Remote Sensing, Vol 15, Iss 11, p 2800 (2023)
With the development of image segmentation technology, image context information plays an increasingly important role in semantic segmentation. However, due to the complexity of context information in different feature maps, simple context capture op
Externí odkaz:
https://doaj.org/article/bb5adbf555254f31982406d31619a94a
Publikováno v:
Neurocomputing. 535:123-133
Publikováno v:
Mathematics; Volume 11; Issue 12; Pages: 2655
Numerous deep learning-based object detection methods have achieved excellent performance. However, the performance on small-size object detection and positive and negative sample imbalance problems is not satisfactory. We propose a multi-scale featu