Zobrazeno 1 - 10
of 181
pro vyhledávání: '"Cheng, Yongmei"'
Data-driven paradigms using machine learning are becoming ubiquitous in image processing and communications. In particular, image-to-image (I2I) translation is a generic and widely used approach to image processing problems, such as image synthesis,
Externí odkaz:
http://arxiv.org/abs/2111.13105
A signed distance function (SDF) as the 3D shape description is one of the most effective approaches to represent 3D geometry for rendering and reconstruction. Our work is inspired by the state-of-the-art method DeepSDF that learns and analyzes the 3
Externí odkaz:
http://arxiv.org/abs/2108.08593
Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting
Externí odkaz:
http://arxiv.org/abs/2103.15726
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing February 2024 208:1-13
Autor:
Yu, Lu, Twardowski, Bartłomiej, Liu, Xialei, Herranz, Luis, Wang, Kai, Cheng, Yongmei, Jui, Shangling, van de Weijer, Joost
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this setting, networks
Externí odkaz:
http://arxiv.org/abs/2004.00440
Publikováno v:
In Measurement 15 November 2023 221
Publikováno v:
In ISA Transactions August 2023 139:122-134
Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image embeddings with
Externí odkaz:
http://arxiv.org/abs/1904.03624
Autor:
Tian, Zhaoxu1 (AUTHOR) tianzx1991@mail.nwpu.edu.cn, Cheng, Yongmei1 (AUTHOR), Yao, Shun1 (AUTHOR), Li, Zhenwei1 (AUTHOR)
Publikováno v:
Remote Sensing. Feb2024, Vol. 16 Issue 4, p612. 22p.