Jingi Ju

Jingi Ju

Auto-generated profile, based on publicly available information

Jingi Ju

Department of Information and Communication Engineering, Hanbat National University, Daejeon 34014, Republic of Korea

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 December 2021 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
SMSEO MINSEOK
SEO MINSEOK
DCDonghyeon Cho
Donghyeon Cho
SLSangwoo Lee
Sangwoo Lee
JPJongchan Park
Jongchan Park
DKDaehan Kim
Daehan Kim
DCDong-Geol Choi
Dong-Geol Choi
The common paradigm of CNN-based action recognition modelsis to simply use the average of the dense predictions from every frame. However, these dense predictions are inefficient since all frames are evenly utilized regardless of the existence of the action. In real-time action recognition applications where the input video is untrimmed, the dense prediction is even more severely inefficient. Instead of these dense predictions, we propose a lightweight CNN-based sampler that selects frames that are relevant to the action in the video. The proposed sampler is trained by a self-supervised learning method that mixes one irrelevant frame in an input video clip and finds that irrelevant frame. With the trained sampler, we select frames to be used as inputs to the action recognition model. Our sampler can be combined with any action recognition models and works independently of them. Through various experiments, we demonstrate that the proposed sampler is not only time and memory-efficient but also significantly increases performance in the action recognition benchmarks, including HMDB51 and UCF101. Finally, we applied the self-supervised sampler to the real-time surveillance system in the subway station, and improved the action recognition performance by 7% with 80% reduction in computation. Code and dataset are available in https://github.com/seominseok0429/SelSupSampler and https://aihub.or.kr/aidata/34124 .

18 August 2024 in Remote Sensing Letters
Verified
Journal Article
Open access
HNHyeonCheol Noh
HyeonCheol Noh
JJJinGi Ju
JinGi Ju
YKYuHyun Kim
YuHyun Kim
MKMinWoo Kim
MinWoo Kim
DCDong-Geol Choi
Dong-Geol Choi

6 February 2024 in IEEE Access
Verified
Journal Article
Open access
JJJingi Ju
Jingi Ju
HNHyeoncheol Noh
Hyeoncheol Noh
YWYooseung Wang
Yooseung Wang
DCDong-Geol Choi
Dong-Geol Choi
Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by self-training with pseudo-labeling pixels having high confidences for unlabeled images. However, using only high-confidence pixels for self-training may result in losing much of the information in the unlabeled sets due to poor confidence calibration of modern deep learning networks. In this paper, we propose a class-wise adaptive strategy for semi supervised semantic segmentation (CASS) to cope with the loss of most information that occurs in existing high-confidence-based pseudo-labeling methods. Unlike existing semi-supervised semantic segmentation frameworks, CASS constructs a validation set on a labeled set, to leverage the calibration performance for each class. On this basis, we propose a calibration aware class-wise adaptive thresholding and class-wise adaptive over-sampling using the analysis results from the validation set. Our proposed CASS achieves state-of-the-art performance on the full data partition of the base PASCAL VOC 2012 dataset and on the 1/4 data partition of the Cityscapes dataset with significant margins of 83.0% and 80.4%, respectively.

4 November 2021 in Electronics
Verified
Journal Article
Open access
PDF file
SLSang-Woo Lee
Sang-Woo Lee
RLRyong Lee
Ryong Lee
SMSEO MINSEOK
SEO MINSEOK
JPJongchan Park
Jongchan Park
HNHyeon-Cheol Noh
Hyeon-Cheol Noh
DCDong-Geol Choi
Dong-Geol Choi
Multi-task learning is a computationally efficient method to solve multiple tasks in one multi-task model, instead of multiple single-task models. MTL is expected to learn both diverse and shareable visual features from multiple datasets. However, MTL performances usually do not outperform single-task learning. Recent MTL methods tend to use heavy task-specific heads with large overheads to generate task-specific features. In this work, we (1) validate the efficacy of MTL in low-data conditions with early-exit architectures, and (2) propose a simple feature filtering module with minimal overheads to generate task-specific features. We assume that, in low-data conditions, the model cannot learn useful low-level features due to the limited amount of data. We empirically show that MTL can significantly improve performances in all tasks under low-data conditions. We further optimize the early-exit architecture by a sweep search on the optimal feature for each task. Furthermore, we propose a feature filtering module that selects features for each task. Using the optimized early-exit architecture with the feature filtering module, we improve the 15.937% in ImageNet and 4.847% in Places365 under the low-data condition where only 5% of the original datasets are available. Our method is empirically validated in various backbones and various MTL settings.

18 November 2024 in Electronics
Verified
Journal Article
Open access
PDF file
MKMin-Woo Kim
Min-Woo Kim
SPSekil Park
Sekil Park
JJJin-Gi Ju
Jin-Gi Ju
HNHyeon-Cheol Noh
Hyeon-Cheol Noh
DCDong-Geol Choi
Dong-Geol Choi
In applications such as environmental monitoring, algorithms and deep learning-based methods using synthetic aperture radar (SAR) and electro-optical (EO) data have been proposed with promising results. These results have been achieved using already cleaned datasets for training data. However, in real-world data collection, data are often collected regardless of environmental noises (clouds, night, missing data, etc.). Without cleaning the data with these noises, the trained model has a critical problem of poor performance. To address these issues, we propose the Clean Collector Algorithm (CCA). First, we use a pixel-based approach to clean the QA60 mask and outliers. Secondly, we remove missing data and night-time data that can act as noise in the training process. Finally, we use a feature-based refinement method to clean the cloud images using FID. We demonstrate its effectiveness by winning first place in the SAR-to-EO translation track of the MultiEarth 2023 challenge. We also highlight the performance and robustness of the CCA on other cloud datasets, SEN12MS-CR-TS and Scotland&India.