Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Sagnik Majumder"'
Publikováno v:
Journal of Imaging, Vol 8, Iss 4, p 93 (2022)
Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the correspo
Externí odkaz:
https://doaj.org/article/a0878655885c448c9104a4da57262038
Autor:
Sagnik Majumder, Kristen Grauman
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198410
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::13160891ad9f1083653f0e2bf37667a8
https://doi.org/10.1007/978-3-031-19842-7_32
https://doi.org/10.1007/978-3-031-19842-7_32
Autor:
Sagnik Majumder, Pratik Narang, Nishad Sahu, Soumendu Sinha, Ravindra Mukhiya, Rishabh Bhardwaj
Publikováno v:
International Journal of Circuit Theory and Applications. 47:954-970
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::935cd7e5a5ab5f7f3a84d0e33c9d9312
https://doi.org/10.1002/cta.2618
https://doi.org/10.1002/cta.2618
Publikováno v:
EACL (Student Research Workshop)
While numerous methods have been proposed as defenses against adversarial examples in question answering (QA), these techniques are often model specific, require retraining of the model, and give only marginal improvements in performance over vanilla
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40657a9b12420f80a8ca00b3e73a1525
http://arxiv.org/abs/2102.03016
http://arxiv.org/abs/2102.03016
We introduce the active audio-visual source separation problem, where an agent must move intelligently in order to better isolate the sounds coming from an object of interest in its environment. The agent hears multiple audio sources simultaneously (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e472af9c1959d05158a9cb7ad7d21f1
Publikováno v:
Journal of Computers. :1067-1074
A simple model of MNIST handwritten digit recognition is presented here. The model is an adaptation of a previous theory of face recognition. It realizes translation and rotation invariance in a principled way instead of being based on extensive lear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b153be3496756b89fdcd4a184072566
https://doi.org/10.17706/jcp.13.9.1067-1074
https://doi.org/10.17706/jcp.13.9.1067-1074
Publikováno v:
ICCV Workshops
We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with extreme value theory based open set recognition. While the former alo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dea257e25510dd7f1f94fb6ebc7fa664
http://arxiv.org/abs/1908.09625
http://arxiv.org/abs/1908.09625
Publikováno v:
Journal of Imaging; Volume 8; Issue 4; Pages: 93
Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the correspo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d061ac65b65b7a199abdc8c8ca63e3a5
http://arxiv.org/abs/1905.12019
http://arxiv.org/abs/1905.12019
Publikováno v:
CVPR
Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c0f9c9fb2d6b6d7af195e7ba608436d7
Autor:
Rishabh Bhardwaj, Ravindra Mukhiya, Soumendu Sinha, Pawan K. Ajmera, Rishi Sharma, Sagnik Majumder, Pratik Narang
Publikováno v:
2017 IEEE Regional Symposium on Micro and Nanoelectronics (RSM).
This paper presents a new Machine Learning based temperature compensation technique for Ion-Sensitive Field-Effect Transistor (ISFET). The circuit models for various electronic devices like MOSFET are available in commercial Technology Computer Aided
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d010b1a759343199128f5cb63af8482
https://doi.org/10.1109/rsm.2017.8069141
https://doi.org/10.1109/rsm.2017.8069141