Zobrazeno 1 - 10
of 10 659
pro vyhledávání: '"Choi Dong"'
The Multimodal Learning Workshop (PBVS 2024) aims to improve the performance of automatic target recognition (ATR) systems by leveraging both Synthetic Aperture Radar (SAR) data, which is difficult to interpret but remains unaffected by weather condi
Externí odkaz:
http://arxiv.org/abs/2412.12565
Autor:
Kang, Haneol, Choi, Dong-Wan
The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the recall-oriented cont
Externí odkaz:
http://arxiv.org/abs/2403.03082
Autor:
Shin, Hyunjune, Choi, Dong-Wan
Data-free knowledge distillation (DFKD) aims to distill pretrained knowledge to a student model with the help of a generator without using original data. In such data-free scenarios, achieving stable performance of DFKD is essential due to the unavai
Externí odkaz:
http://arxiv.org/abs/2402.12406
In general, deep learning-based video frame interpolation (VFI) methods have predominantly focused on estimating motion vectors between two input frames and warping them to the target time. While this approach has shown impressive performance for lin
Externí odkaz:
http://arxiv.org/abs/2311.11602
This paper analyzes the contagion effects associated with the failure of Silicon Valley Bank (SVB) and identifies bank-specific vulnerabilities contributing to the subsequent declines in banks' stock returns. We find that uninsured deposits, unrealiz
Externí odkaz:
http://arxiv.org/abs/2308.06642
The Multimodal Learning for Earth and Environment Workshop (MultiEarth 2023) aims to harness the substantial amount of remote sensing data gathered over extensive periods for the monitoring and analysis of Earth's ecosystems'health. The subtask, Mult
Externí odkaz:
http://arxiv.org/abs/2306.12626
Autor:
Bashkirova, Dina, Mishra, Samarth, Lteif, Diala, Teterwak, Piotr, Kim, Donghyun, Alladkani, Fadi, Akl, James, Calli, Berk, Bargal, Sarah Adel, Saenko, Kate, Kim, Daehan, Seo, Minseok, Jeon, YoungJin, Choi, Dong-Geol, Ettedgui, Shahaf, Giryes, Raja, Abu-Hussein, Shady, Xie, Binhui, Li, Shuang
Label-efficient and reliable semantic segmentation is essential for many real-life applications, especially for industrial settings with high visual diversity, such as waste sorting. In industrial waste sorting, one of the biggest challenges is the e
Externí odkaz:
http://arxiv.org/abs/2303.14828
Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with pseudo-labelin
Externí odkaz:
http://arxiv.org/abs/2303.11606
Autor:
Kim, Daehan, Seo, Minseok, Park, Kwanyong, Shin, Inkyu, Woo, Sanghyun, Kweon, In-So, Choi, Dong-Geol
Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the source and target samples to obt
Externí odkaz:
http://arxiv.org/abs/2303.09779
Publikováno v:
Cell Stress & Chaperones, 2023 Nov 01. 28(6), 835-847.
Externí odkaz:
https://www.jstor.org/stable/48759910
