Zobrazeno 1 - 10
of 365
pro vyhledávání: '"Byung Cheol Song"'
Publikováno v:
IEEE Access, Vol 12, Pp 109690-109701 (2024)
Deep neural networks are generally very vulnerable to adversarial attacks. In order to defend against adversarial attacks in classifiers, Adversarial Purification (AP) was developed to neutralize adversarial perturbations using a generative model at
Externí odkaz:
https://doaj.org/article/30bcbd208fbd48fca32db7b3dae85f4d
Autor:
Seongho Kim, Byung Cheol Song
Publikováno v:
IEEE Access, Vol 12, Pp 72860-72870 (2024)
Ultrasound images acquired through various measuring devices may have different styles, and each style may be specialized for diagnosing specific diseases. Accordingly, ultrasound image-to-image translation (US I2I) has become an essential research f
Externí odkaz:
https://doaj.org/article/2961e611bdf048aab829254e2bac3820
Publikováno v:
IEEE Access, Vol 12, Pp 67847-67859 (2024)
This paper presents an identity-invariant facial expression recognition framework. It aims to make a facial expression recognition (FER) model independently understand facial expressions and identity (ID) attributes such as gender, age, and skin, whi
Externí odkaz:
https://doaj.org/article/74beb1a28a3246c681992a254290e720
Publikováno v:
IEEE Access, Vol 12, Pp 29154-29165 (2024)
Real-time Monte Carlo denoising aims to denoise a 1spp-rendered image with a limited time budget. Many latest techniques for real-time Monte Carlo denoising utilize temporal accumulation (TA) as a pre-processing to improve the temporal stability of s
Externí odkaz:
https://doaj.org/article/8307200eaf104d5494bdd05375e1a37f
Publikováno v:
IEEE Access, Vol 12, Pp 15016-15025 (2024)
In general, salient object detection (SOD) datasets have ambiguity due to annotation accuracy and human subjectivity in determining saliency. Since this data uncertainty causes inaccurate prediction, many techniques tackling data uncertainty have bee
Externí odkaz:
https://doaj.org/article/9497c4af4f034453bc921dd626512d09
Publikováno v:
IEEE Access, Vol 11, Pp 112015-112026 (2023)
This paper presents a framework for effectively applying knowledge distillation (KD) to super-resolution (SR) tasks for computer graphics (CG) images. Specifically, we propose TAKDSR, a KD framework for SR using a teacher assistant (TA) network. Rece
Externí odkaz:
https://doaj.org/article/5b4a2c0da71844c18f976431aba28a29
Publikováno v:
IEEE Access, Vol 11, Pp 87902-87916 (2023)
An image in a display device under strong illuminance can be perceived as darker than the original due to the nature of the human visual system (HVS). In order to alleviate this degradation in terms of software, existing schemes employ global luminan
Externí odkaz:
https://doaj.org/article/29f8795282d14ffdb63f71070ddc1932
Publikováno v:
IEEE Access, Vol 10, Pp 123212-123224 (2022)
This paper proposes various techniques that help Vision Transformer (ViT) to learn small-size datasets from scratch successfully. ViT, which applied the transformer structure to the image classification task, has outperformed convolutional neural net
Externí odkaz:
https://doaj.org/article/32158be2382740b0952eb4e376f8daba
Publikováno v:
IEEE Access, Vol 10, Pp 78446-78454 (2022)
For a long time, anomaly localization has been widely used in industries. Previous studies focused on approximating the distribution of normal features without adaptation to a target dataset. However, since anomaly localization should precisely discr
Externí odkaz:
https://doaj.org/article/576a457cb90b478ab8b3669a605a47fb
Autor:
Dae Ha Kim, Byung Cheol Song
Publikováno v:
IEEE Access, Vol 10, Pp 7439-7459 (2022)
Similarity learning which is useful for the purpose of comparing various characteristics of images in the computer vision field has been often applied for deep metric learning (DML). Also, a lot of combinations of pairwise similarity metrics such as
Externí odkaz:
https://doaj.org/article/88bc23efd1e640f2affb6f0acaa11c37