Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Singhal, Utkarsh"'
Autor:
Singhal, Utkarsh, Cheung, Brian, Chandra, Kartik, Ragan-Kelley, Jonathan, Tenenbaum, Joshua B., Poggio, Tomaso A., Yu, Stella X.
How much can you say about the gradient of a neural network without computing a loss or knowing the label? This may sound like a strange question: surely the answer is "very little." However, in this paper, we show that gradients are more structured
Externí odkaz:
http://arxiv.org/abs/2312.04709
Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too much or too
Externí odkaz:
http://arxiv.org/abs/2309.16672
Multi-spectral imagery is invaluable for remote sensing due to different spectral signatures exhibited by materials that often appear identical in greyscale and RGB imagery. Paired with modern deep learning methods, this modality has great potential
Externí odkaz:
http://arxiv.org/abs/2211.11797
We study complex-valued scaling as a type of symmetry natural and unique to complex-valued measurements and representations. Deep Complex Networks (DCN) extends real-valued algebra to the complex domain without addressing complex-valued scaling. SurR
Externí odkaz:
http://arxiv.org/abs/2112.01525
Autor:
Tancik, Matthew, Srinivasan, Pratul P., Mildenhall, Ben, Fridovich-Keil, Sara, Raghavan, Nithin, Singhal, Utkarsh, Ramamoorthi, Ravi, Barron, Jonathan T., Ng, Ren
We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains. These results shed light on recent advances in computer vision and
Externí odkaz:
http://arxiv.org/abs/2006.10739
Autor:
Shahani, Rakesh, Singhal, Utkarsh
Publikováno v:
Mineral Economics: Raw Materials Report; Sep2023, Vol. 36 Issue 3, p413-425, 13p
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
We study complex-valued scaling as a type of symmetry natural and unique to complex-valued measurements and representations. Deep Complex Networks (DCN) extends real-valued algebra to the complex domain without addressing complex-valued scaling. SurR
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d8dffecc72123992ad002bee4665bd8
https://doi.org/10.1109/cvpr52688.2022.00076
https://doi.org/10.1109/cvpr52688.2022.00076
Autor:
Lescroart, Mark D, Singhal, Utkarsh
Publikováno v:
MODVIS Workshop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______540::138ad76ed37fa8bc766e049dcb6d3b3c
https://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1154&context=modvis
https://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1154&context=modvis
Publikováno v:
Journal of Mines, Metals & Fuels; Aug2018, Vol. 66 Issue 8, p462-471, 4p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.