Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Youngjune Gwon"'
Autor:
Seongho Joe, Byoungjip Kim, Hoyoung Kang, Kyoungwon Park, Bogun Kim, Jaeseon Park, Joonseok Lee, Youngjune Gwon
The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines clusterin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2de8d3e5f87a18e0874e83d7780685d6
Publikováno v:
Proceedings of the International AAAI Conference on Web and Social Media. 9:582-585
We present a data-driven approach for Twitter geolocation and regional classification. Our method is based on sparse coding and dictionary learning, an unsupervised method popular in computer vision and pattern recognition. Through a series of optimi
Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization
Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks including ab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d98afd3b0aa5c19b1b1674893ed811c7
http://arxiv.org/abs/2209.00278
http://arxiv.org/abs/2209.00278
Autor:
Jihoon Kim, Seungjai Min, Young-Joon Choi, Ilhwan Kwon, Jongwon Choi, Jin-Yeop Chang, Youngjune Gwon
Publikováno v:
AAAI
We describe an unsupervised domain adaptation framework for images by a transform to an abstract intermediate domain and ensemble classifiers seeking a consensus. The intermediate domain can be thought as a latent domain where both the source and tar
The advancement in numerous generative models has a two-fold effect: a simple and easy generation of realistic synthesized images, but also an increased risk of malicious abuse of those images. Thus, it is important to develop a generalized detector
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53688b6a17558fb00151c43f800b2bbb
http://arxiv.org/abs/2109.00911
http://arxiv.org/abs/2109.00911
Publikováno v:
ICPR
A Lite BERT (ALBERT) has been introduced to scale up deep bidirectional representation learning for natural languages. Due to the lack of pretrained ALBERT models for Korean language, the best available practice is the multilingual model or resorting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c6610e08eb647d62846fcb0cd23ad001
http://arxiv.org/abs/2101.11363
http://arxiv.org/abs/2101.11363
Publikováno v:
ICPR
Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in sentence-pair
Autor:
Changhyun Park, Jongwon Choi, Sehyeon Park, Seungjai Min, Youngjune Gwon, Minki Hong, Yonghyun Jeong, Doyeon Kim
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695439
ACCV (6)
ACCV (6)
Recently, online transactions have had an exponential growth and expanded to various cases, such as opening bank accounts and filing for insurance claims. Despite the effort of many companies requiring their own mobile applications to capture images
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa8dd3163a23f1f52766b73f42b1b373
https://doi.org/10.1007/978-3-030-69544-6_6
https://doi.org/10.1007/978-3-030-69544-6_6
Autor:
Youngjune Gwon, Hyung Jin Chang, Jinho Choo, Jongwon Choi, Kwang Moo Yi, Byoungjip Kim, Jin-Yeop Chang, Ji-Hoon Kim
Publikováno v:
CVPR
Active Learning for discriminative models has largely been studied with the focus on individual samples, with less emphasis on how classes are distributed or which classes are hard to deal with. In this work, we show that this is harmful. We propose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::748ec6cd504d8567c69a76fab7e463ba
http://arxiv.org/abs/2003.11249
http://arxiv.org/abs/2003.11249
Publikováno v:
IEEE Transactions on Cognitive Communications and Networking. 2:95-109
We introduce competing cognitive resilient network (CCRN) of mobile radios challenged to optimize data throughput and networking efficiency under dynamic spectrum access and adversarial threats (e.g., jamming). Unlike the conventional approaches, CCR