no code implementations • 18 Jul 2023 • Jaeyoung Kim, Kyuheon Jung, Dongbin Na, Sion Jang, Eunbin Park, Sungchul Choi
The surrogate OOD sample introduced by POE shows a similar representation to ID data, which is most effective in training a rejection network.
no code implementations • 5 Apr 2023 • Bo Qian, Hao Chen, Xiangning Wang, Haoxuan Che, Gitaek Kwon, Jaeyoung Kim, Sungjin Choi, Seoyoung Shin, Felix Krause, Markus Unterdechler, Junlin Hou, Rui Feng, Yihao Li, Mostafa El Habib Daho, Qiang Wu, Ping Zhang, Xiaokang Yang, Yiyu Cai, Weiping Jia, Huating Li, Bin Sheng
Computer-assisted automatic analysis of diabetic retinopathy (DR) is of great importance in reducing the risks of vision loss and even blindness.
1 code implementation • 13 Feb 2023 • Jaeyoung Kim, Dongbin Na, Sungchul Choi, Sungbin Lim
We find that the ensemble model overfitted to the training set shows sub-par calibration performance and also observe that PLMs trained with confidence penalty loss have a trade-off between calibration and accuracy.
1 code implementation • 26 Dec 2022 • Jaeyoung Kim, Seo Taek Kong, Dongbin Na, Kyu-Hwan Jung
We first deduce that OOD images are perceived by a deep neural network to be semantically similar to in-distribution samples when they share a common background, as deep networks are observed to incorrectly classify such images with high confidence.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 18 Oct 2022 • Gitaek Kwon, Eunjin Kim, Sunho Kim, Seongwon Bak, Minsung Kim, Jaeyoung Kim
Recently, diabetic retinopathy (DR) screening utilizing ultra-wide optical coherence tomography angiography (UW-OCTA) has been used in clinical practices to detect signs of early DR.
1 code implementation • 5 Oct 2022 • Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vlad Karpukhin, Yi Lu, Minjoon Seo
The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed.
no code implementations • 31 May 2022 • Ripon Kumar Saha, A. M. Mahmud Chowdhury, Kyung-Sun Na, Gyu Deok Hwang, Youngsub Eom, Jaeyoung Kim, Hae-Gon Jeon, Ho Sik Hwang, Euiheon Chung
Purpose: Develop a deep learning-based automated method to segment meibomian glands (MG) and eyelids, quantitatively analyze the MG area and MG ratio, estimate the meiboscore, and remove specular reflections from infrared images.
no code implementations • 27 May 2022 • Soheil Khorram, Jaeyoung Kim, Anshuman Tripathi, Han Lu, Qian Zhang, Hasim Sak
This paper introduces contrastive siamese (c-siam) network, an architecture for leveraging unlabeled acoustic data in speech recognition.
no code implementations • 6 May 2021 • Jaeyoung Kim, Han Lu, Anshuman Tripathi, Qian Zhang, Hasim Sak
From LibriSpeech evaluation, self alignment outperformed existing schemes: 25% and 56% less delay compared to FastEmit and constrained alignment at the similar word error rate.
no code implementations • 21 Oct 2020 • Jaewoong Choi, Sion Jang, Jaeyoung Kim, Jiho Lee, Janghyeok Yoona, Sungchul Choi
In this study, we address the challenges in developing a deep learning-based automatic patent citation recommendation system.
no code implementations • 7 Oct 2020 • Anshuman Tripathi, Jaeyoung Kim, Qian Zhang, Han Lu, Hasim Sak
In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model.
2 code implementations • 7 Sep 2020 • Youngtaek Kim, Jaeyoung Kim, Hyeon Jeon, Young-Ho Kim, Hyunjoo Song, Bohyoung Kim, Jinwook Seo
Furthermore, they do not scale for large and complex Git commit graphs, which can play an important role in understanding the overall development history.
Software Engineering Human-Computer Interaction
no code implementations • Interspeech 2019 • Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
Second, three loss functions based on SDR, PESQ and STOI are proposed to minimize the metric mismatch.
Sound Audio and Speech Processing
no code implementations • 13 Oct 2019 • Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
Transformer neural networks (TNN) demonstrated state-of-art performance on many natural language processing (NLP) tasks, replacing recurrent neural networks (RNNs), such as LSTMs or GRUs.
Audio and Speech Processing Sound
no code implementations • 26 Jan 2019 • Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
First, the network optimization is performed on the time-domain signals after ISTFT to avoid spectrum mismatch.
no code implementations • 12 Aug 2018 • Jaeyoung Kim, Sion Jang, Sungchul Choi, Eunjeong Park
This paper presents an empirical exploration of the use of capsule networks for text classification.
no code implementations • 27 Oct 2017 • Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
Despite the remarkable progress achieved on automatic speech recognition, recognizing far-field speeches mixed with various noise sources is still a challenging task.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
3 code implementations • 10 Jan 2017 • Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee
The residual LSTM provides an additional spatial shortcut path from lower layers for efficient training of deep networks with multiple LSTM layers.