Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Sapkota, Suman"'
Autor:
Sapkota, Suman, Bhattarai, Binod
Global Neuron Importance Estimation is used to prune neural networks for efficiency reasons. To determine the global importance of each neuron or convolutional kernel, most of the existing methods either use activation or gradient information or both
Externí odkaz:
http://arxiv.org/abs/2310.20203
Computer-assisted treatment has emerged as a viable application of medical imaging, owing to the efficacy of deep learning models. Real-time inference speed remains a key requirement for such applications to help medical personnel. Even though there
Externí odkaz:
http://arxiv.org/abs/2306.13203
Autor:
Sapkota, Suman, Bhattarai, Binod
Network Morphism based Neural Architecture Search (NAS) is one of the most efficient methods, however, knowing where and when to add new neurons or remove dis-functional ones is generally left to black-box Reinforcement Learning models. In this paper
Externí odkaz:
http://arxiv.org/abs/2207.04467
Autor:
Sapkota, Suman, Thapa, Bipin, Chen, Jingxuan, Zunong, Jiawulan, Asihaer, Yeerlin, Li, Menglong, Ji, Xiaohui, Ding, Ding, Li, Hui, Ma, Boyuan, Vermund, Sten H., Shu, Mushui, Hu, Yifei
Publikováno v:
In Ecotoxicology and Environmental Safety 1 September 2024 282
In this paper we present our solution to extract albedo of branded labels for e-commerce products. To this end, we generate a large-scale photo-realistic synthetic data set for albedo extraction followed by training a generative model to translate im
Externí odkaz:
http://arxiv.org/abs/2109.02929
Autor:
Sapkota, Suman, Bhattarai, Binod
Connected decision boundaries are useful in several tasks like image segmentation, clustering, alpha-shape or defining a region in nD-space. However, the machine learning literature lacks methods for generating connected decision boundaries using neu
Externí odkaz:
http://arxiv.org/abs/2106.08748
Multi-domain image-to-image translation with conditional Generative Adversarial Networks (GANs) can generate highly photo realistic images with desired target classes, yet these synthetic images have not always been helpful to improve downstream supe
Externí odkaz:
http://arxiv.org/abs/2105.05501
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Sapkota, Suman
The structures which seem to be strong may collapse during an earthquake. This was the case of the Pyne Gould Corporation building in New Zealand, which collapsed during the February 22, 2011, earthquake. Its collapse raised questions about the perfo
Autor:
Menglong Li, Wen Shu, Yuchen Zou, Huidi Xiao, Asihaer, Yeerlin, Mengying Guan, Khattab, Nourhan, Thapa, Bipin, Sapkota, Suman, Vermund, Sten H., Dayong Huang, Yifei Hu
Publikováno v:
American Journal of Gastroenterology (Lippincott Williams & Wilkins); Aug2024, Vol. 119 Issue 8, p1640-1643, 4p