Sung Jae Hwang

Abstract Theoretically, domain adaptation is a well-researched problem. Further, this theory has been well-used in practice. In particular, we note the bound on target error given by Ben-David et al. (Mach Learn 79(1–2):151–175, 2010) and the well-known domain-aligning algorithm based on this work using Domain Adversarial Neural Networks (DANN) presented by Ganin and Lempitsky (in International conference on machine learning, pp 1180–1189). Recently, multiple variants of DANN have been proposed

Visual relationships provide higher-level information of objects and their relations in an image - this enables a semantic understanding of the scene and helps downstream applications. Given a set of localized objects in some training data, visual relationship detection seeks to detect the most likely "relationship" between objects in a given image. While the specific objects may be well represented in training data, their relationships may still be infrequent. The empirical distribution obtaine

Modern neuroimaging studies frequently combine data collected from multiple scanners and experimental conditions. Such data often contain substantial technical variability associated with image intensity scale (image intensity scales are not the same in different images) and scanner effects (images obtained from different scanners contain substantial technical biases). Here we evaluate and compare results of data analysis methods without any data transformation (RAW), with intensity normalizatio

Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks. Although data augmentation is a standard approach to compensate for the scarcity of data, it has been less explored in the point cloud literature. In this paper, we propose a simple and effective augmentation method called PointWOLF for point cloud augmentation. The proposed method produces smoothly varying non-rigid deformations by locally weighted transformations c

Characterizing Alzheimer's disease (AD) at pre-clinical stages is crucial for initiating early treatment strategies. It is widely accepted that amyloid accumulation is a primary pathological event in AD. Also, loss of connectivity between brain regions is suspected of contributing to cognitive decline, but studies that test these associations using either local (i.e., individual edges) or global (i.e., modularity) connectivity measures may be limited. In this study, we utilized data acquired fro

Sit to stand (STS) movement is one of the most common activity in daily life. In addition, Korean traditionally stand up from various sitting heights in one’s daily life compared to other foreigners. As Korea enter rapidly to the aging society, needs of the elderly’s independent life are increasing. Therefore the importance of research about the analysis of elderly’s activity in daily life is rapidly increasing. In this study, we analyzed joint movements and changes of muscle length during STS(

uncertainty estimation for powerful sequential models such as GRUs.

Leveraging semantically precise pseudo masks derived from image-level class knowledge for segmentation, namely image-level Weakly Supervised Semantic Segmentation (WSSS), remains challenging. Class Activation Maps (CAMs) using CNNs enhance WSSS by focusing on specific class parts like only the face of a human, whereas Vision Transformers (ViT) capture broader semantic parts but often miss complete class-specific details, such as human bodies with nearby objects like dogs. In this work, we propos

There is a great deal of interest in using large scale brain imaging studies to understand how brain connectivity evolves over time for an individual and how it varies over different levels/quantiles of cognitive function. To do so, one typically performs so-called tractography procedures on diffusion MR brain images and derives measures of brain connectivity expressed as graphs. The nodes correspond to distinct brain regions and the edges encode the strength of the connection. The scientific in

In this study, we developed an active ankle-foot orthosis(AAFO) which can control dorsi/ plantar flexion of the ankle joint to prevent foot drop and toe drag during walking. 3D gait analyses were performed on five healthy subjects under three different gait conditions: the normal gait without AFO, the SAFO gait with the conventional plastic AFO, and the AAFO gait with the developed AFO. As a result, the developed AAFO preeminently induced the normal gait compared to the SAFO. Additionally, AAFO

Eigenvalue problems are ubiquitous in computer vision, covering a very broad spectrum of applications ranging from estimation problems in multi-view geometry to image segmentation. Few other linear algebra problems have a more mature set of numerical routines available and many computer vision libraries leverage such tools extensively. However, the ability to call the underlying solver only as a "black box" can often become restrictive. Many 'human in the loop' settings in vision frequently expl

Video is one of the richest sources of information available online but extracting deep insights from video content at internet scale is still an open problem, both in terms of depth and breadth of understanding, as well as scale. Over the last few years, the field of video understanding has made great strides due to the availability of large-scale video datasets and core advances in image, audio, and video modeling architectures. However, the state-of-the-art architectures on small scale datase

Osteoporosis, a bone disease characterized by decreased bone mineral density (BMD) resulting in decreased mechanical strength and an increased fracture risk, remains poorly understood in children. Herein, we developed/validated a deep learning-based model to predict pediatric BMD using plain spine radiographs. Using a two-stage model, Yolov8 was applied for vertebral body detection to predict BMD values using a regression model based on ResNet-18, from which a low-BMD group was classified based