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 • 8 Apr 2021 • Seo Taek Kong, Soomin Jeon, Dongbin Na, Jaewon Lee, Hong-Seok Lee, Kyu-Hwan Jung
Although unlabeled data is readily available in pool-based AL, AL algorithms are usually evaluated by measuring the increase in supervised learning (SL) performance at consecutive acquisition steps.
no code implementations • 1 Jan 2021 • Seo Taek Kong, Soomin Jeon, Jaewon Lee, Hong-Seok Lee, Kyu-Hwan Jung
We name this AL scheme convergence rate control (CRC), and our experiments show that a deep neural network trained using a combination of CRC and a recently proposed SSL algorithm can quickly achieve high performance using far less labeled samples than SL.
no code implementations • 2 Sep 2019 • Woong Bae, Seungho Lee, Yeha Lee, Beomhee Park, Minki Chung, Kyu-Hwan Jung
We propose the resource-optimized neural architecture search method which can be applied to 3D medical segmentation tasks in a short training time (1. 39 days for 1GB dataset) using a small amount of computation power (one RTX 2080Ti, 10. 8GB GPU memory).
no code implementations • 21 Nov 2018 • Sejin Park, Woochan Hwang, Kyu-Hwan Jung
Machine learning applications in medical imaging are frequently limited by the lack of quality labeled data.
no code implementations • 2 Nov 2018 • Jaemin Son, Woong Bae, Sangkeun Kim, Sang Jun Park, Kyu-Hwan Jung
Fundoscopic images are often investigated by ophthalmologists to spot abnormal lesions to make diagnoses.
2 code implementations • 28 Jun 2017 • Jaemin Son, Sang Jun Park, Kyu-Hwan Jung
Retinal vessel segmentation is an indispensable step for automatic detection of retinal diseases with fundoscopic images.