Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Ryu, Jongbin"'
We propose an efficient interactive method for multi-head self-attention via decomposition. For existing methods using multi-head self-attention, the attention operation of each head is computed independently. However, we show that the interactions b
Externí odkaz:
http://arxiv.org/abs/2402.17507
We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (\ie, classification heads) instead of relying on channel expansion or additional building blocks. Our approach employs attention-based a
Externí odkaz:
http://arxiv.org/abs/2310.16483
Autor:
Holste, Gregory, Zhou, Yiliang, Wang, Song, Jaiswal, Ajay, Lin, Mingquan, Zhuge, Sherry, Yang, Yuzhe, Kim, Dongkyun, Nguyen-Mau, Trong-Hieu, Tran, Minh-Triet, Jeong, Jaehyup, Park, Wongi, Ryu, Jongbin, Hong, Feng, Verma, Arsh, Yamagishi, Yosuke, Kim, Changhyun, Seo, Hyeryeong, Kang, Myungjoo, Celi, Leo Anthony, Lu, Zhiyong, Summers, Ronald M., Shih, George, Wang, Zhangyang, Peng, Yifan
Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long
Externí odkaz:
http://arxiv.org/abs/2310.16112
Publikováno v:
ICCVW 2023
In real medical data, training samples typically show long-tailed distributions with multiple labels. Class distribution of the medical data has a long-tailed shape, in which the incidence of different diseases is quite varied, and at the same time,
Externí odkaz:
http://arxiv.org/abs/2308.05542
Autor:
Park, Wongi, Ryu, Jongbin
Classifying fine-grained lesions is challenging due to minor and subtle differences in medical images. This is because learning features of fine-grained lesions with highly minor differences is very difficult in training deep neural networks. Therefo
Externí odkaz:
http://arxiv.org/abs/2308.05770
Autor:
Go, Junhyung, Ryu, Jongbin
In this paper, we introduce the spatial bias to learn global knowledge without self-attention in convolutional neural networks. Owing to the limited receptive field, conventional convolutional neural networks suffer from learning long-range dependenc
Externí odkaz:
http://arxiv.org/abs/2302.12505
Publikováno v:
In Computer Methods and Programs in Biomedicine June 2024 251
Autor:
Holste, Gregory, Zhou, Yiliang, Wang, Song, Jaiswal, Ajay, Lin, Mingquan, Zhuge, Sherry, Yang, Yuzhe, Kim, Dongkyun, Nguyen-Mau, Trong-Hieu, Tran, Minh-Triet, Jeong, Jaehyup, Park, Wongi, Ryu, Jongbin, Hong, Feng, Verma, Arsh, Yamagishi, Yosuke, Kim, Changhyun, Seo, Hyeryeong, Kang, Myungjoo, Celi, Leo Anthony, Lu, Zhiyong, Summers, Ronald M., Shih, George, Wang, Zhangyang, Peng, Yifan
Publikováno v:
In Medical Image Analysis October 2024 97
Autor:
Park, Wongi, Ryu, Jongbin
Publikováno v:
In Computers in Biology and Medicine May 2024 174
Publikováno v:
In Biomedical Signal Processing and Control May 2024 91