Zobrazeno 1 - 10
of 224
pro vyhledávání: '"Xu, Hai Ming"'
As an effective way to alleviate the burden of data annotation, semi-supervised learning (SSL) provides an attractive solution due to its ability to leverage both labeled and unlabeled data to build a predictive model. While significant progress has
Externí odkaz:
http://arxiv.org/abs/2309.04659
Autor:
Wang, Shuo, Zhao, Xinhai, Xu, Hai-Ming, Chen, Zehui, Yu, Dameng, Chang, Jiahao, Yang, Zhen, Zhao, Feng
Multi-view 3D object detection (MV3D-Det) in Bird-Eye-View (BEV) has drawn extensive attention due to its low cost and high efficiency. Although new algorithms for camera-only 3D object detection have been continuously proposed, most of them may risk
Externí odkaz:
http://arxiv.org/abs/2303.01686
Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation, i.e., region
Externí odkaz:
http://arxiv.org/abs/2210.04388
Open-set panoptic segmentation (OPS) problem is a new research direction aiming to perform segmentation for both \known classes and \unknown classes, i.e., the objects ("things") that are never annotated in the training set. The main challenges of OP
Externí odkaz:
http://arxiv.org/abs/2207.02504
Semi-supervised learning is a promising way to reduce the annotation cost for text-classification. Combining with pre-trained language models (PLMs), e.g., BERT, recent semi-supervised learning methods achieved impressive performance. In this work, w
Externí odkaz:
http://arxiv.org/abs/2205.10189
Autor:
Zuo, Ying-Bing, Wen, Zeng-Jin, Cheng, Meng-Die, Jia, Dong-Dong, Zhang, Yi-Fei, Yang, Hong-Yu, Xu, Hai-Ming, Xin, Hui, Zhang, Yin-Feng
Publikováno v:
In Ecotoxicology and Environmental Safety 15 October 2024 285
Publikováno v:
In Environmental Pollution 15 September 2024 357
Autor:
Lin, Yu-Jia, Li, Hong-Mei, Gao, Yan-Rong, Wu, Ping-Fan, Cheng, Bin, Yu, Chen-Long, Sheng, Yu-Xin, Xu, Hai-Ming
Publikováno v:
In Environmental Pollution 1 June 2024 350
Self-supervised learning (SlfSL), aiming at learning feature representations through ingeniously designed pretext tasks without human annotation, has achieved compelling progress in the past few years. Very recently, SlfSL has also been identified as
Externí odkaz:
http://arxiv.org/abs/2001.02865
Autor:
Shan, Jing, Wu, Meng-Yu, Zhang, Ying-Chi, Lin, Yu-Jia, Cheng, Bin, Gao, Yan-Rong, Liu, Zhi-Hong, Xu, Hai-Ming
Publikováno v:
In Cytokine June 2023 166