Search Results for author: Hong-Gyu Jung

Found 9 papers, 0 papers with code

Spatial Reasoning for Few-Shot Object Detection

no code implementations2 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.

Data Augmentation Few-Shot Object Detection +2

GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints

no code implementations16 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.

Weakly Supervised Thoracic Disease Localization via Disease Masks

no code implementations25 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.

Visual Question Answering based on Local-Scene-Aware Referring Expression Generation

no code implementations22 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.

Question Answering Referring Expression +2

Few-Shot Object Detection via Knowledge Transfer

no code implementations28 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.

Few-Shot Object Detection Object +2

Few-Shot Learning with Geometric Constraints

no code implementations20 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.

Few-Shot Learning

Interpreting Undesirable Pixels for Image Classification on Black-Box Models

no code implementations27 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.

Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.