no code implementations • 2 Nov 2022 • Geonuk Kim, Hong-Gyu Jung, Seong-Whan Lee
Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples.
no code implementations • 16 Aug 2021 • Ji-Hoon Kim, Sang-Hoon Lee, Ji-Hyun Lee, Hong-Gyu Jung, Seong-Whan Lee
While numerous attempts have been made to the few-shot speaker adaptation system, there is still a gap in terms of speaker similarity to the target speaker depending on the amount of data.
no code implementations • 25 Jan 2021 • Hyun-Woo Kim, Hong-Gyu Jung, Seong-Whan Lee
To enable a deep learning-based system to be used in the medical domain as a computer-aided diagnosis system, it is essential to not only classify diseases but also present the locations of the diseases.
no code implementations • 22 Jan 2021 • Jung-Jun Kim, Dong-Gyu Lee, Jialin Wu, Hong-Gyu Jung, Seong-Whan Lee
We quantitatively and qualitatively evaluated the proposed method on the VQA v2 dataset and compared it with state-of-the-art methods in terms of answer prediction.
no code implementations • 28 Aug 2020 • Geonuk Kim, Hong-Gyu Jung, Seong-Whan Lee
If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.
no code implementations • 5 Aug 2020 • Hong-Gyu Jung, Sin-Han Kang, Hee-Dong Kim, Dong-Ok Won, Seong-Whan Lee
The masking step aims to select an important feature from the input data to be classified as a target class.
no code implementations • 1 Apr 2020 • Jin-Woo Seo, Hong-Gyu Jung, Seong-Whan Lee
Few-shot learning aims to classify unseen classes with a few training examples.
no code implementations • 20 Mar 2020 • Hong-Gyu Jung, Seong-Whan Lee
We assume a network trained for base categories with a large number of training examples, and we aim to add novel categories to it that have only a few, e. g., one or five, training examples.
no code implementations • 27 Sep 2019 • Sin-Han Kang, Hong-Gyu Jung, Seong-Whan Lee
To tackle this issue, in this paper, we propose an explanation method that visualizes undesirable regions to classify an image as a target class.