Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Suraj Srinivas"'
Autor:
Suraj Srinivas, Andrey Kuzmin, Markus Nagel, Mart van Baalen, Andrii Skliar, Tijmen Blankevoort
Current methods for pruning neural network weights iteratively apply magnitude-based pruning on the model weights and re-train the resulting model to recover lost accuracy. In this work, we show that such strategies do not allow for the recovery of e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16579bbdb2cbdb0a8d87caf77bd29b0b
http://arxiv.org/abs/2202.01290
http://arxiv.org/abs/2202.01290
Publikováno v:
CVPR Workshops
The emergence of Deep neural networks has seen human-level performance on large scale computer vision tasks such as image classification. However these deep networks typically contain large amount of parameters due to dense matrix multiplications and
Autor:
Konda Reddy Mopuri, Suraj Srinivas, Nikita Prabhu, R. Venkatesh Babu, Ravi Kiran Sarvadevabhatla, Srinivas S S Kruthiventi
Publikováno v:
Deep Learning for Medical Image Analysis
Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep learning techniques have offered a compelling alternative – that of aut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c88745ebd6f0cf4f11fed9055aa8d9a0
https://doi.org/10.1016/b978-0-12-810408-8.00003-1
https://doi.org/10.1016/b978-0-12-810408-8.00003-1
Autor:
R. Venkatesh Babu, Yaniv Bar, Joseph Blair, Andrew P. Bradley, Gustavo Carneiro, Hao Chen, Erik B. Dam, Idit Diamant, Qi Dou, Michael D. Feldman, Renee Frank, Yaozong Gao, Bogdan Georgescu, Ofer Geva, Florin C. Ghesu, Hayit Greenspan, Yanrong Guo, Pheng-Ann Heng, Joachim Hornegger, R. Todd Hurst, Christian Igel, Vamsi K. Ithapu, Andrew Janowczyk, Sterling C. Johnson, Michiel Kallenberg, Christopher B. Kendall, Minjeong Kim, Eli Konen, Srinivas S.S. Kruthiventi, Jianming Liang, Rui Liao, Sivan Lieberman, Le Lu, Anant Madabhushi, Kenneth B. Margulies, Dimitris Metaxas, Shun Miao, Vincent C.T. Mok, Konda R. Mopuri, Jacinto Nascimento, Hien Van Nguyen, Mads Nielsen, Jeffrey J. Nirschl, Akshay Pai, Eliot G. Peyster, Nikita Prabhu, Jing Qin, Ravi K. Sarvadevabhatla, Dinggang Shen, Lin Shi, Hoo-Chang Shin, Jae Y. Shin, Vikas Singh, Stefan Sommer, Suraj Srinivas, Heung-Il Suk, Ronald M. Summers, Nima Tajbakhsh, Yuan-Ching Teng, Raviteja Vemulapalli, Defeng Wang, Jane Z. Wang, Shaoyu Wang, Lior Wolf, Guorong Wu, Yuanpu Xie, Fuyong Xing, Zhennan Yan, Lin Yang, Lequan Yu, Yiqiang Zhan, Shaoting Zhang, Lei Zhao, S. Kevin Zhou, Xiang Sean Zhou, Gali Zimmerman
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::08515dc6c341cb0e65d35266883668cf
https://doi.org/10.1016/b978-0-12-810408-8.00029-8
https://doi.org/10.1016/b978-0-12-810408-8.00029-8
Publikováno v:
ICVGIP
Rotation invariance has been studied in the computer vision community primarily in the context of small in-plane rotations. This is usually achieved by building invariant image features. However, the problem of achieving invariance for large rotation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de3b230438ae38c6757d596cef3ea58c
http://arxiv.org/abs/1611.05744
http://arxiv.org/abs/1611.05744
Autor:
Suraj Srinivas, R. Venkatesh Babu
Publikováno v:
BMVC
Deep neural networks with millions of parameters are at the heart of many state of the art machine learning models today. However, recent works have shown that models with much smaller number of parameters can also perform just as well. In this work,
Autor:
R. Venkatesh Babu, Suraj Srinivas
Publikováno v:
BMVC
Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art computer vision systems today. However, recent works have shown that much smaller models can achieve similar levels of performance. In this work, we address
Publikováno v:
ICIP
The blurred images obtained using conventional cameras usually lack high-frequency details due to the impulse response associated with long exposure. This leads to imperfect reconstruction of the underlying scene. It has been shown that flutter-shutt