Zobrazeno 1 - 10
of 199
pro vyhledávání: '"guo, Haiyun"'
Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the subsequent dat
Externí odkaz:
http://arxiv.org/abs/2411.06171
Autor:
Xie, Mingyang, Guo, Haiyun, Feng, Brandon Y., Jin, Lingbo, Veeraraghavan, Ashok, Metzler, Christopher A.
Imaging through scattering media is a fundamental and pervasive challenge in fields ranging from medical diagnostics to astronomy. A promising strategy to overcome this challenge is wavefront modulation, which induces measurement diversity during ima
Externí odkaz:
http://arxiv.org/abs/2404.07985
Autor:
Zhou, Haowen, Feng, Brandon Y., Guo, Haiyun, Lin, Siyu, Liang, Mingshu, Metzler, Christopher A., Yang, Changhuei
Image stacks provide invaluable 3D information in various biological and pathological imaging applications. Fourier ptychographic microscopy (FPM) enables reconstructing high-resolution, wide field-of-view image stacks without z-stack scanning, thus
Externí odkaz:
http://arxiv.org/abs/2310.18529
Background subtraction (BGS) aims to extract all moving objects in the video frames to obtain binary foreground segmentation masks. Deep learning has been widely used in this field. Compared with supervised-based BGS methods, unsupervised methods hav
Externí odkaz:
http://arxiv.org/abs/2303.14679
Autor:
Guo, Haiyun
Three-dimensional (3D) reconstruction plays an important role in imaging research filed. Structured light technology has been widely used in 3D imaging, recognition and measurement, indicating great industrial and commercial value. In this thesis, a
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identi
Externí odkaz:
http://arxiv.org/abs/2206.06607
In person re-identification (ReID), very recent researches have validated pre-training the models on unlabelled person images is much better than on ImageNet. However, these researches directly apply the existing self-supervised learning (SSL) method
Externí odkaz:
http://arxiv.org/abs/2203.03931
Autor:
Li, Mingyu, Liu, Xiaohui, Li, Jing, Guo, Haiyun, Xue, Shanshan, Zhu, Lei, Ma, Cuicui, Chen, Dongyu, Wang, Huaning, Cai, Yanhui, Shen, Jiangpei
Publikováno v:
In Brain Research 1 December 2024 1844
Autor:
Guo, Haiyun, Li, Yumeng, Wang, Shiquan, Yang, Yongheng, Xu, Tiantian, Zhao, Jianshuai, Wang, Jin, Zuo, Wenqiang, Wang, Pengju, Zhao, Guangchao, Wang, Huaning, Hou, Wugang, Dong, Hailong, Cai, Yanhui
Publikováno v:
In Redox Biology August 2024 74
In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-based methods only locate the human parts coarsely, or rely on pretrain
Externí odkaz:
http://arxiv.org/abs/2104.00921