Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Park, Sunjong"'
Autor:
Choi, Kanghyun, Lee, Hye Yoon, Kwon, Dain, Park, SunJong, Kim, Kyuyeun, Park, Noseong, Lee, Jinho
Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset. Although several DFQ methods have been proposed for vision trans
Externí odkaz:
http://arxiv.org/abs/2407.20021
Autor:
Lee, Hyeyoon, Choi, Kanghyun, Kwon, Dain, Park, Sunjong, Jaiswal, Mayoore Selvarasa, Park, Noseong, Choi, Jonghyun, Lee, Jinho
Recent advances in adversarial robustness rely on an abundant set of training data, where using external or additional datasets has become a common setting. However, in real life, the training data is often kept private for security and privacy issue
Externí odkaz:
http://arxiv.org/abs/2406.15635
Autor:
Suh, Sangwon, Park, Sunjong
In this paper, we describe the top-scoring submissions for team RTZR VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22) in the closed dataset, speaker verification Track 1. The top performed system is a fusion of 7 models, which contains 3 diffe
Externí odkaz:
http://arxiv.org/abs/2209.10147
In this study, we train deep neural networks to classify composer on a symbolic domain. The model takes a two-channel two-dimensional input, i.e., onset and note activations of time-pitch representation, which is converted from MIDI recordings and pe
Externí odkaz:
http://arxiv.org/abs/2010.00823
Publikováno v:
The Journal of Convergence Society and Public Policy. 11:153-168
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9009b07e4f343a42c0967f4bbcef95c4
https://doi.org/10.37582/cspp.2017.11.2.153
https://doi.org/10.37582/cspp.2017.11.2.153
