Dasol Hong(홍다솔)
I am a master's student advised by Professor Hyun Myung at KAIST (Urban Robotics Lab).
Publications
-
Object-Aware Domain Generalization for Object Detection
Wooju Lee*, Dasol Hong*, Hyungtae Lim†, Hyun Myung†, in AAAI, 2024Abstract
Single-domain generalization (S-DG) aims to generalize a model to unseen environments with a single-source domain. However, most S-DG approaches have been conducted in the field of classification. When these approaches are applied to object detection, the semantic features of some objects can be damaged, which can lead to imprecise object localization and misclassification. To address these problems, we propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection. Our method consists of data augmentation and training strategy, which are called OA-Mix and OA-Loss, respectively. OA-Mix generates multi-domain data with multi-level transformation and object-aware mixing strategy. OA-Loss enables models to learn domain-invariant representations for objects and backgrounds from the original and OA-Mixed images. Our proposed method outperforms state-of-the-art works on standard benchmarks. -
이미지를 강인하게 인식하는 보조 노이즈 전파 기법
이우주*, 홍다솔, 이인균, 명현†, in 한국로봇학회 (KROS), 2023Abstract
In this study, we propose an auxiliary noise propagation module that is robust to an unstructured environment. Deep neural networks show high classification performance when training and testing data are drawn from the independent and identical distribution. However, deep neural networks show significantly low performance for the out-of-distribution data. Augmented noisy images could be the solution, but they degrade the model performance for the original data distribution. Our proposed model balances and improves performance for both cases. Our model propagates the original images to the original batch normalization layer and augmented noisy images to the auxiliary batch normalization layer separately. Separate batch normalization layers enforce the model to learn various features and improve the robustness for out-of-distribution data. Auxiliary noise propagation is trained on CIFAR-10 and the performance of the module is evaluated on the CIFAR-10-C. Experimental results show that the proposed auxiliary noise propagation improves the robustness for out-of-distribution data. -
X-MAS: Extremely Large-Scale Multi-Modal Sensor Dataset for Outdoor Surveillance in Real Environments
DongKi Noh*, Changki Sung, Teayoung Uhm, WooJu Lee, Hyungtae Lim, Jaeseok Choi, Kyuewang Lee, Dasol Hong, Daeho Um, Inseop Chung, Hochul Shin, MinJung Kim, Hyoung-Rock Kim, SeungMin Baek, Hyun Myung†, in IEEE Robotics and Automation Letters (R-AL), 2023Abstract
In robotics and computer vision communities, extensive studies have been widely conducted regarding surveillance tasks, including human detection, tracking, and motion recognition with a camera. Additionally, deep learning algorithms are widely utilized in the aforementioned tasks as in other computer vision tasks. Existing public datasets are insufficient to develop learning-based methods that handle various surveillance for outdoor and extreme situations such as harsh weather and low illuminance conditions. Therefore, we introduce a new large-scale outdoor surveillance dataset named e X tremely large-scale M ulti-mod A l S ensor dataset ( X-MAS ) containing more than 500,000 image pairs and the first-person view data annotated by well-trained annotators. Moreover, a single pair contains multi-modal data (e.g. an IR image, an RGB image, a thermal image, a depth image, and a LiDAR scan). ... -
자율주행차량의 실시간 다중센서 데이터 수집·정제·분석 및 관제 통합 플랫폼 개발
홍다솔*, 김가연, 박다혜, 윤영호, 김학일†, in 제어·로봇·시스템학회 학술대회 (ICROS), 2021Abstract
DIVA2 is an integrated platform for real-time multi-sensor data collection, refining, analysis, and control of autonomous vehicle.
Projects
Pneumonia Classification
CNN-based pneumonia classifier
Through CNN, chest X-ray images are classified into three levels (normal, bacterial, and viral pneumonia).
DIVA2
Integrated platform for real-time multi-sensor data collection, purification, analysis and control of autonomous vehicles
An integrated platform for real-time multi-sensor data collection, refinement, analysis, and control of autonomous vehicles.
Smart Automatic Feeder
Design of an automatic feeder that reduces the burden when caring for pets
Accesses the memory address of the MCU (ATmega4809) to control load cells, motors, Bluetooth modules, etc.
INCAR
Android-Based Carpool Application
Frontend was developed through Android Studio. Servers and databases were built with AWS EC2 and MySQL.