Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Manoj Ghuhan"'
The emerging paradigm of federated learning strives to enable collaborative training of machine learning models on the network edge without centrally aggregating raw data and hence, improving data privacy. This sharply deviates from traditional machi
Externí odkaz:
http://arxiv.org/abs/1912.00818
Autor:
Pahwa, Ramit, Arivazhagan, Manoj Ghuhan, Garg, Ankur, Krishnamoorthy, Siddarth, Saxena, Rohit, Choudhary, Sunav
Deploying trained convolutional neural networks (CNNs) to mobile devices is a challenging task because of the simultaneous requirements of the deployed model to be fast, lightweight and accurate. Designing and training a CNN architecture that does we
Externí odkaz:
http://arxiv.org/abs/1911.12740
Autor:
Divya Kothandaraman, Sumit Shekhar, Abhilasha Sancheti, Manoj Ghuhan, Tripti Shukla, Dinesh Manocha
We present a novel method, SALAD, for the challenging vision task of adapting a pre-trained "source" domain network to a "target" domain, with a small budget for annotation in the "target" domain and a shift in the label space. Further, the task assu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6bee465c224583b2642e474f9d285bc3
http://arxiv.org/abs/2205.12840
http://arxiv.org/abs/2205.12840
Publikováno v:
SIGIR
Image search engines rely on appropriately designed ranking features that capture various aspects of the content semantics as well as the historic popularity. In this work, we consider the role of colour in this relevance matching process. Our work i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01cd51d87f1acda8c0d1dc0a4d1802b2