1 code implementation • 26 Jan 2023 • Athul Shibu, Abhishek Kumar, Heechul Jung, Dong-Gyu Lee
Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks.
1 code implementation • 1 Jun 2022 • Jiuk Hong, Chaehyeon Lee, Soyoun Bang, Heechul Jung
Transformers have been successfully used in various fields and are becoming the standard tools in computer vision.
no code implementations • 19 Nov 2021 • Jaesin Ahn, Jiuk Hong, Jeongwoo Ju, Heechul Jung
The proposed method achieved $71. 4\%$ with a few parameters (of $3. 1M$) on the ImageNet-1k dataset compared to that required by the original transformer model of XCiT-N12 ($69. 9\%$).
1 code implementation • 31 May 2021 • Chaehyeon Lee, Junghoon Seo, Heechul Jung
In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because they cause domain changes.
1 code implementation • 5 Mar 2021 • Jeongwoo Ju, Heechul Jung, Yoonju Oh, Junmo Kim
Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data.
1 code implementation • CVPR 2021 • Jaemin Na, Heechul Jung, Hyung Jin Chang, Wonjun Hwang
However, most of the studies were based on direct adaptation from the source domain to the target domain and have suffered from large domain discrepancies.
Ranked #3 on Domain Adaptation on Office-31
1 code implementation • 24 Sep 2019 • Min-Kook Choi, Heechul Jung
With the improvements in the object detection networks, several variations of object detection networks have been achieved impressive performance.
no code implementations • 20 Feb 2018 • Min-Kook Choi, Jaehyeong Park, Jihun Jung, Heechul Jung, Jin-Hee Lee, Woong Jae Won, Woo Young Jung, Jincheol Kim, Soon Kwon
We used an MS-COCO detection dataset to verify the performance of the proposed SSL method and deformable neural networks (D-ConvNets) as an object detector for basic training.
no code implementations • 16 Nov 2017 • Heechul Jung, Jeongwoo Ju, Minju Jung, Junmo Kim
Expanding the domain that deep neural network has already learned without accessing old domain data is a challenging task because deep neural networks forget previously learned information when learning new data from a new domain.
no code implementations • 12 Sep 2017 • Han S. Lee, Heechul Jung, Alex A. Agarwal, Junmo Kim
To verify how DNNs understand the relatedness between object classes, we conducted experiments on the image database provided in cognitive psychology.
no code implementations • 20 Dec 2016 • Heechul Jung, Min-Kook Choi, Kwon Soon, Woo Young Jung
Traditional pedestrian collision warning systems sometimes raise alarms even when there is no danger (e. g., when all pedestrians are walking on the sidewalk).
no code implementations • 1 Jul 2016 • Heechul Jung, Jeongwoo Ju, Minju Jung, Junmo Kim
Surprisingly, our method is very effective to forget less of the information in the source domain, and we show the effectiveness of our method using several experiments.
no code implementations • ICCV 2015 • Heechul Jung, Sihaeng Lee, Junho Yim, Sunjeong Park, Junmo Kim
Furthermore, we show that our new integration method gives more accurate results than traditional methods, such as a weighted summation and a feature concatenation method.
no code implementations • CVPR 2015 • Junho Yim, Heechul Jung, ByungIn Yoo, Changkyu Choi, Dusik Park, Junmo Kim
This paper proposes a new deep architecture based on a novel type of multitask learning, which can achieve superior performance in rotating to a target-pose face image from an arbitrary pose and illumination image while preserving identity.
no code implementations • 5 Mar 2015 • Heechul Jung, Sihaeng Lee, Sunjeong Park, Injae Lee, Chunghyun Ahn, Junmo Kim
Furthermore, one of the main contributions of this paper is that our deep network catches the facial action points automatically.
no code implementations • CVPR 2014 • Heechul Jung, Jeongwoo Ju, Junmo Kim
For evaluation of our algorithm, Hopkins 155 dataset, which is a representative test set for rigid motion segmentation, is adopted; it consists of two and three rigid motions.