Zobrazeno 1 - 10
of 6 446
pro vyhledávání: '"Clark, James"'
Autor:
Yuan, Ye, Zhang, Youyuan, Chen, Can, Wu, Haolun, Li, Zixuan, Li, Jianmo, Clark, James J., Liu, Xue
Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. A prevalent approach involves training a conditional generative model on existing designs and their associated
Externí odkaz:
http://arxiv.org/abs/2405.13964
Conventional image quality metrics (IQMs), such as PSNR and SSIM, are designed for perceptually uniform gamma-encoded pixel values and cannot be directly applied to perceptually non-uniform linear high-dynamic-range (HDR) colors. Similarly, most of t
Externí odkaz:
http://arxiv.org/abs/2405.00670
Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling in diffus
Externí odkaz:
http://arxiv.org/abs/2403.06269
Autor:
Tayaranian, Mohammadreza, Mozafari, Seyyed Hasan, Clark, James J., Meyer, Brett, Gross, Warren
SWIN transformer is a prominent vision transformer model that has state-of-the-art accuracy in image classification tasks. Despite this success, its unique architecture causes slower inference compared with similar deep neural networks. Integer quant
Externí odkaz:
http://arxiv.org/abs/2402.01169
This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and making use of the duality between network weights and layer inputs. We ca
Externí odkaz:
http://arxiv.org/abs/2401.13212
It is necessary to develop efficient DNNs deployed on edge devices with limited computation resources. However, the compressed networks often execute new tasks in the target domain, which is different from the source domain where the original network
Externí odkaz:
http://arxiv.org/abs/2401.12014
Autor:
Ghonge, Sudarshan, Brandt, Joshua, Sullivan, J. M., Millhouse, Margaret, Chatziioannou, Katerina, Clark, James A., Littenberg, Tyson, Cornish, Neil, Hourihane, Sophie, Cadonati, Laura
We investigate the impact of transient noise artifacts, or {\it glitches}, on gravitational wave inference, and the efficacy of data cleaning procedures in recovering unbiased source properties. Due to their time-frequency morphology, broadband glitc
Externí odkaz:
http://arxiv.org/abs/2311.09159
Autor:
Clark, James G.1
Publikováno v:
History Today. Mar2024, Vol. 74 Issue 3, p54-63. 10p.
Text in English with abstracts in English, isiZulu and Xhosa
This research applies the Near Repeat Calculator (NRC) to identify near repeat residential burglary patterns in the Hillcrest (KZN) policing area for the first time. A total of 490 res
This research applies the Near Repeat Calculator (NRC) to identify near repeat residential burglary patterns in the Hillcrest (KZN) policing area for the first time. A total of 490 res
Externí odkaz:
http://uir.unisa.ac.za/handle/10500/25683