Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Vasudeva, Bhavya"'
Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of the inductive biases that they have and how those biases are different from other neural network architectures remains elusive. Various neural ne
Externí odkaz:
http://arxiv.org/abs/2403.06925
Self-attention, the core mechanism of transformers, distinguishes them from traditional neural networks and drives their outstanding performance. Towards developing the fundamental optimization principles of self-attention, we investigate the implici
Externí odkaz:
http://arxiv.org/abs/2402.05738
Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the model making biased predictions wh
Externí odkaz:
http://arxiv.org/abs/2310.06161
Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract the most in
Externí odkaz:
http://arxiv.org/abs/2108.09335
Autor:
Vasudeva, Bhavya, Tian, Runfeng, Wu, Dee H., James, Shirley A., Refai, Hazem H., He, Fei, Yang, Yuan
Many physical, biological and neural systems behave as coupled oscillators, with characteristic phase coupling across different frequencies. Methods such as $n:m$ phase locking value and bi-phase locking value have previously been proposed to quantif
Externí odkaz:
http://arxiv.org/abs/2102.10471
Autor:
Ignatov, Andrey, Timofte, Radu, Zhang, Zhilu, Liu, Ming, Wang, Haolin, Zuo, Wangmeng, Zhang, Jiawei, Zhang, Ruimao, Peng, Zhanglin, Ren, Sijie, Dai, Linhui, Liu, Xiaohong, Li, Chengqi, Chen, Jun, Ito, Yuichi, Vasudeva, Bhavya, Deora, Puneesh, Pal, Umapada, Guo, Zhenyu, Zhu, Yu, Liang, Tian, Li, Chenghua, Leng, Cong, Pan, Zhihong, Li, Baopu, Kim, Byung-Hoon, Song, Joonyoung, Ye, Jong Chul, Baek, JaeHyun, Zhussip, Magauiya, Koishekenov, Yeskendir, Ye, Hwechul Cho, Liu, Xin, Hu, Xueying, Jiang, Jun, Gu, Jinwei, Li, Kai, Tan, Pengliang, Hou, Bingxin
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-qualit
Externí odkaz:
http://arxiv.org/abs/2011.04994
Compressive sensing (CS) is widely used to reduce the acquisition time of magnetic resonance imaging (MRI). Although state-of-the-art deep learning based methods have been able to obtain fast, high-quality reconstruction of CS-MR images, their main d
Externí odkaz:
http://arxiv.org/abs/2002.10523
Compressive sensing magnetic resonance imaging (CS-MRI) accelerates the acquisition of MR images by breaking the Nyquist sampling limit. In this work, a novel generative adversarial network (GAN) based framework for CS-MRI reconstruction is proposed.
Externí odkaz:
http://arxiv.org/abs/1910.06067
In this paper, the field programmable gate array (FPGA) implementation of a fetal heart rate (FHR) monitoring system is presented. The system comprises of a preprocessing unit to remove various types of noise, followed by a fetal electrocardiogram (F
Externí odkaz:
http://arxiv.org/abs/1910.07496
Autor:
Vasudeva, Bhavya, Tian, Runfeng, Wu, Dee H., James, Shirley A., Refai, Hazem H., Ding, Lei, He, Fei, Yang, Yuan
Publikováno v:
In Biomedical Signal Processing and Control April 2022 74