Zobrazeno 1 - 10
of 78
pro vyhledávání: '"Feng, Yingchao"'
Autor:
Bi, Hanbo, Feng, Yingchao, Mao, Yongqiang, Pei, Jianning, Diao, Wenhui, Wang, Hongqi, Sun, Xian
Few-shot Segmentation (FSS) aims to segment the interested objects in the query image with just a handful of labeled samples (i.e., support images). Previous schemes would leverage the similarity between support-query pixel pairs to construct the pix
Externí odkaz:
http://arxiv.org/abs/2409.17453
Autor:
Diao, Wenhui, Yu, Haichen, Kang, Kaiyue, Ling, Tong, Liu, Di, Feng, Yingchao, Bi, Hanbo, Ren, Libo, Li, Xuexue, Mao, Yongqiang, Sun, Xian
Aerial Remote Sensing (ARS) vision tasks pose significant challenges due to the unique characteristics of their viewing angles. Existing research has primarily focused on algorithms for specific tasks, which have limited applicability in a broad rang
Externí odkaz:
http://arxiv.org/abs/2409.13366
Autor:
Bi, Hanbo, Feng, Yingchao, Diao, Wenhui, Wang, Peijin, Mao, Yongqiang, Fu, Kun, Wang, Hongqi, Sun, Xian
For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed feature enc
Externí odkaz:
http://arxiv.org/abs/2409.10389
Autor:
Bi, Hanbo, Feng, Yingchao, Yan, Zhiyuan, Mao, Yongqiang, Diao, Wenhui, Wang, Hongqi, Sun, Xian
Few-shot segmentation (FSS) is proposed to segment unknown class targets with just a few annotated samples. Most current FSS methods follow the paradigm of mining the semantics from the support images to guide the query image segmentation. However, s
Externí odkaz:
http://arxiv.org/abs/2310.12452
The balance between high accuracy and high speed has always been a challenging task in semantic image segmentation. Compact segmentation networks are more widely used in the case of limited resources, while their performances are constrained. In this
Externí odkaz:
http://arxiv.org/abs/2107.08591
Autor:
Sun, Xian, Wang, Peijin, Yan, Zhiyuan, Xu, Feng, Wang, Ruiping, Diao, Wenhui, Chen, Jin, Li, Jihao, Feng, Yingchao, Xu, Tao, Weinmann, Martin, Hinz, Stefan, Wang, Cheng, Fu, Kun
With the rapid development of deep learning, many deep learning-based approaches have made great achievements in object detection task. It is generally known that deep learning is a data-driven method. Data directly impact the performance of object d
Externí odkaz:
http://arxiv.org/abs/2103.05569
Publikováno v:
In Journal of Manufacturing Processes 31 January 2024 110:91-100
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
The performance of object instance segmentation in remote sensing images has been greatly improved through the introduction of many landmark frameworks based on convolutional neural network. However, the object densely issue still affects the accurac
Externí odkaz:
http://arxiv.org/abs/1904.09823
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing April 2022 186:19-33