Search Results - "Jeon, Eun Som"

Robust Time Series Recovery and Classification Using Test-Time Noise Simulator Networks by Jeon, Eun Som, Lohit, Suhas, Anirudh, Rushil, Turaga, Pavan

“…Time-series are commonly susceptible to various types of corruption due to sensor-level changes and defects which can result in missing samples, sensor and…”
Get full text

Constrained Adaptive Distillation Based on Topological Persistence for Wearable Sensor Data by Jeon, Eun Som, Choi, Hongjun, Shukla, Ankita, Wang, Yuan, Buman, Matthew P., Turaga, Pavan

“…Wearable sensor data analysis with persistence features generated by topological data analysis (TDA) has achieved great success in various applications, and…”
Get full text

Uncertainty-Aware Topological Persistence Guided Knowledge Distillation on Wearable Sensor Data by Jeon, Eun Som, Buman, Matthew P., Turaga, Pavan

“…In applications involving analysis of the wearable sensor data, machine learning techniques that use features from the topological data analysis (TDA) have…”
Get full text

Topological Knowledge Distillation for Wearable Sensor Data by Jeon, Eun Som, Choi, Hongjun, Shukla, Ankita, Wang, Yuan, Buman, Matthew P., Turaga, Pavan

“…Converting wearable sensor data to actionable health insights has witnessed large interest in recent years. Deep learning methods have been utilized in and…”
Get full text

Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data by Jeon, Eun Som, Som, Anirudh, Shukla, Ankita, Hasanaj, Kristina, Buman, Matthew P., Turaga, Pavan

“…Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems…”
Get full text

Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study by Choi, Hongjun, Jeon, Eun Som, Shukla, Ankita, Turaga, Pavan

“…Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the…”
Get full text

Human detection based on the generation of a background image by using a far-infrared light camera by Jeon, Eun Som, Choi, Jong-Suk, Lee, Ji Hoon, Shin, Kwang Yong, Kim, Yeong Gon, Le, Toan Thanh, Park, Kang Ryoung

“…The need for computer vision-based human detection has increased in fields, such as security, intelligent surveillance and monitoring systems. However,…”
Get full text

Robust pedestrian detection by combining visible and thermal infrared cameras by Lee, Ji Hoon, Choi, Jong-Suk, Jeon, Eun Som, Kim, Yeong Gon, Le, Toan Thanh, Shin, Kwang Yong, Lee, Hyeon Chang, Park, Kang Ryoung

“…With the development of intelligent surveillance systems, the need for accurate detection of pedestrians by cameras has increased. However, most of the…”
Get full text

Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data by Jeon, Eun Som, Choi, Hongjun, Shukla, Ankita, Wang, Yuan, Lee, Hyunglae, Buman, Matthew P, Turaga, Pavan

“…Engineering Applications of Artificial Intelligence, 130, 107719 (2024) Deep learning methods have achieved a lot of success in various applications involving…”
Get full text

Leveraging Angular Distributions for Improved Knowledge Distillation by Jeon, Eun Som, Choi, Hongjun, Shukla, Ankita, Turaga, Pavan

“…Neurocomputing, Volume 518, 2023, Pages 466-481 Knowledge distillation as a broad class of methods has led to the development of lightweight and memory…”
Get full text

Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data by Jeon, Eun Som, Som, Anirudh, Shukla, Ankita, Hasanaj, Kristina, Buman, Matthew P, Turaga, Pavan

“…Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems…”
Get full text

Leveraging angular distributions for improved knowledge distillation by Jeon, Eun Som, Choi, Hongjun, Shukla, Ankita, Turaga, Pavan

“…Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a…”
Get full text

Topological persistence guided knowledge distillation for wearable sensor data by Jeon, Eun Som, Choi, Hongjun, Shukla, Ankita, Wang, Yuan, Lee, Hyunglae, Buman, Matthew P., Turaga, Pavan

“…Deep learning methods have achieved a lot of success in various applications involving converting wearable sensor data to actionable health insights. A common…”
Get full text

Knowledge Distillation with Geometric Approaches for Multimodal Data Analysis by Jeon, Eun Som

“…This thesis presents robust and novel solutions using knowledge distillation with geometric approaches and multimodal data that can address the current…”
Get full text

Human Detection Based on the Generation of a Background Image and Fuzzy System by Using a Thermal Camera by Jeon, Eun Som, Kim, Jong Hyun, Hong, Hyung Gil, Batchuluun, Ganbayar, Park, Kang Ryoung

“…Recently, human detection has been used in various applications. Although visible light cameras are usually employed for this purpose, human detection based on…”
Get full text

Leveraging Topological Guidance for Improved Knowledge Distillation by Jeon, Eun Som, Khurana, Rahul, Pathak, Aishani, Turaga, Pavan

“…Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex…”
Get full text

Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study by Choi, Hongjun, Jeon, Eun Som, Shukla, Ankita, Turaga, Pavan

“…Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the…”
Get full text

Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation by Nath, Utkarsh, Goel, Rajeev, Jeon, Eun Som, Kim, Changhoon, Min, Kyle, Yang, Yezhou, Yang, Yingzhen, Turaga, Pavan

“…To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice…”
Get full text

Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks by Hong, Jinyung, Jeon, Eun Som, Kim, Changhoon, Park, Keun Hee, Nath, Utkarsh, Yang, Yezhou, Turaga, Pavan, Pavlic, Theodore P

“…Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for…”
Get full text