Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Hwang, Wonjun"'
Multi-target domain adaptation (MTDA) for semantic segmentation poses a significant challenge, as it involves multiple target domains with varying distributions. The goal of MTDA is to minimize the domain discrepancies among a single source and multi
Externí odkaz:
http://arxiv.org/abs/2403.11582
Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the reliance o
Externí odkaz:
http://arxiv.org/abs/2403.11537
Autor:
Do, Dinh Phat, Kim, Taehoon, Na, Jaemin, Kim, Jiwon, Lee, Keonho, Cho, Kyunghwan, Hwang, Wonjun
Domain adaptation for object detection typically entails transferring knowledge from one visible domain to another visible domain. However, there are limited studies on adapting from the visible to the thermal domain, because the domain gap between t
Externí odkaz:
http://arxiv.org/abs/2403.09359
The teacher-student framework, prevalent in semi-supervised semantic segmentation, mainly employs the exponential moving average (EMA) to update a single teacher's weights based on the student's. However, EMA updates raise a problem in that the weigh
Externí odkaz:
http://arxiv.org/abs/2310.18640
Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new informatio
Externí odkaz:
http://arxiv.org/abs/2305.05175
Autor:
Lee, Daeseok1 (AUTHOR) dsleemaths@gmail.com, Hwang, Wonjun1 (AUTHOR), Byun, Jeunghyun1 (AUTHOR), Shin, Bonggun1,2 (AUTHOR) nomolos79@gmail.com
Publikováno v:
BMC Bioinformatics. 9/20/2024, Vol. 25 Issue 1, p1-26. 26p.
In knowledge distillation, since a single, omnipotent teacher network cannot solve all problems, multiple teacher-based knowledge distillations have been studied recently. However, sometimes their improvements are not as good as expected because some
Externí odkaz:
http://arxiv.org/abs/2206.01186
Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational efficiency. I
Externí odkaz:
http://arxiv.org/abs/2205.15531
The objective of human parsing is to partition a human in an image into constituent parts. This task involves labeling each pixel of the human image according to the classes. Since the human body comprises hierarchically structured parts, each body p
Externí odkaz:
http://arxiv.org/abs/2111.14173
Recent unsupervised domain adaptation methods have utilized vicinal space between the source and target domains. However, the equilibrium collapse of labels, a problem where the source labels are dominant over the target labels in the predictions of
Externí odkaz:
http://arxiv.org/abs/2111.13353