Zobrazeno 1 - 10
of 346
pro vyhledávání: '"Song, Byung Cheol"'
Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive learning p
Externí odkaz:
http://arxiv.org/abs/2304.11173
Autor:
Kim, Daeha, Song, Byung Cheol
Identity-invariant facial expression recognition (FER) has been one of the challenging computer vision tasks. Since conventional FER schemes do not explicitly address the inter-identity variation of facial expressions, their neural network models sti
Externí odkaz:
http://arxiv.org/abs/2209.12172
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:
http://arxiv.org/abs/2206.04325
Autor:
Lee, Seunghyun, Song, Byung Cheol
Conventional NAS-based pruning algorithms aim to find the sub-network with the best validation performance. However, validation performance does not successfully represent test performance, i.e., potential performance. Also, although fine-tuning the
Externí odkaz:
http://arxiv.org/abs/2203.02651
Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a large-size da
Externí odkaz:
http://arxiv.org/abs/2112.13492
Model-agnostic meta-learning (MAML) is a well-known optimization-based meta-learning algorithm that works well in various computer vision tasks, e.g., few-shot classification. MAML is to learn an initialization so that a model can adapt to a new task
Externí odkaz:
http://arxiv.org/abs/2110.10353
Autor:
Jeong, Seogsong, Park, Sun Jae, Na, Seong Kyun, Park, Sang Min, Song, Byung-Cheol, Oh, Yun Hwan
Publikováno v:
In Hepatobiliary & Pancreatic Diseases International August 2024 23(4):353-360
Publikováno v:
In Neurocomputing 1 June 2024 584
Autor:
Lee, Seunghyun, Song, Byung Cheol
Knowledge distillation (KD) is one of the most useful techniques for light-weight neural networks. Although neural networks have a clear purpose of embedding datasets into the low-dimensional space, the existing knowledge was quite far from this purp
Externí odkaz:
http://arxiv.org/abs/2104.13561
Autor:
Kang, Dohee, Kim, Daeha, Kang, Donghyun, Kim, Taein, Lee, Bowon, Kim, Deokhwan, Song, Byung Cheol
Publikováno v:
In Expert Systems With Applications January 2024 235