Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Sung Ho Bae"'
Publikováno v:
Electronics Letters, Vol 59, Iss 23, Pp n/a-n/a (2023)
Abstract Despite the recent upsurge of self‐supervised methods in single image denoising, achieving robustness and efficiency of performance is still challenging due to some prevalent issues like identity mapping, overfitting, and increased varianc
Externí odkaz:
https://doaj.org/article/3ebf58257aec49699dd51d25dafec637
Publikováno v:
IEEE Access, Vol 11, Pp 96449-96459 (2023)
Batch Normalization (BatchNorm) is an effective architectural component in deep learning models that helps to improve model performance and speed up training. However, it has also been found to increase the vulnerability of models to adversarial atta
Externí odkaz:
https://doaj.org/article/bec15144ef58418b9179bbe73c999749
Autor:
Jung-Heum Kang, Muhammad Salman Ali, Hye-Won Jeong, Chang-Kyun Choi, Younhee Kim, Se Yoon Jeong, Sung-Ho Bae, Hui Yong Kim
Publikováno v:
IEEE Access, Vol 11, Pp 34198-34209 (2023)
Recently, video and image compression methods using neural networks have received much attention. In MPEG standardization, Video Coding for Machine (VCM) is a newly arising topic which attempts to compress features/images for the purpose of machine v
Externí odkaz:
https://doaj.org/article/b6a7bb195f694b359b47a043fd21d93a
Publikováno v:
IEEE Access, Vol 11, Pp 15460-15470 (2023)
Substantial research has been done in saliency modeling to make intelligent machines that can perceive and interpret their surroundings and focus only on the salient regions in a visual scene. But existing spatio–temporal saliency models either tre
Externí odkaz:
https://doaj.org/article/53886144739a4fd883aa1c45ea4bb703
Publikováno v:
IEEE Access, Vol 10, Pp 133969-133980 (2022)
Modern displays have the capability of rendering video contents encoded with high dynamic range (HDR) standards. HDR contents deliver more realistic visual experiences by wider color gamut and luminance compared to standard dynamic range (SDR) conten
Externí odkaz:
https://doaj.org/article/fc9a2d658656445b9c328a0f03adaf19
Autor:
Awais Muhammad, Sung-Ho Bae
Publikováno v:
IEEE Access, Vol 10, Pp 118815-118830 (2022)
Deep learning has revolutionized computer vision with phenomenal success and widespread applications. Despite impressive results in complex problems, neural networks are susceptible to adversarial attacks: small and imperceptible changes in input spa
Externí odkaz:
https://doaj.org/article/98230c1162e74412b6321fa6466cd721
Publikováno v:
IEEE Access, Vol 10, Pp 81988-82002 (2022)
In recent years, researchers have been working to interpret the insights of deep neural networks in the pursuit of overcoming their opaqueness and so-called ‘black-box’ tag. In this work, we present a new posthoc visual interpretation technique t
Externí odkaz:
https://doaj.org/article/1dff9f9c40ff44c99ffffd1e73d94be4
Publikováno v:
IEEE Access, Vol 10, Pp 88251-88262 (2022)
Some conventional transforms such as Discrete Walsh-Hadamard Transform (DWHT) and Discrete Cosine Transform (DCT) have been widely used as feature extractors in image processing but rarely applied in neural networks. However, we found that these conv
Externí odkaz:
https://doaj.org/article/97ba8a0e0d034adab9aaf2723da06925
Autor:
Kang-Ho Lee, Sung-Ho Bae
Publikováno v:
IEEE Access, Vol 9, Pp 69601-69608 (2021)
Because of resource-constrained environments, network compression has become an essential part of deep neural networks research. In this paper, we found a mutual relationship between kernel weights termed as Inter-Layer Kernel Correlation (ILKC). The
Externí odkaz:
https://doaj.org/article/e7128ab35e0d4e7883c9a33f9791b002
Publikováno v:
IEEE Access, Vol 9, Pp 93998-94009 (2021)
Deep neural networks (DNNs) for single image super-resolution (SISR) tend to have large model size and high computation complexity to achieve promising restoration performance. Unlike image classification, model compression for SISR has rarely been s
Externí odkaz:
https://doaj.org/article/02b7f2a9dd0e4c7caa017b7b25fab918