Search Results for author: Hyunwoo J. Kim

Found 29 papers, 15 papers with code

Invertible Monotone Operators for Normalizing Flows

1 code implementation15 Oct 2022 Byeongkeun Ahn, Chiyoon Kim, Youngjoon Hong, Hyunwoo J. Kim

Normalizing flows model probability distributions by learning invertible transformations that transfer a simple distribution into complex distributions.

Density Estimation

TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers

1 code implementation14 Oct 2022 Hyeong Kyu Choi, Joonmyung Choi, Hyunwoo J. Kim

To this end, we propose TokenMixup, an efficient attention-guided token-level data augmentation method that aims to maximize the saliency of a mixed set of tokens.

Data Augmentation Image Classification

SageMix: Saliency-Guided Mixup for Point Clouds

1 code implementation13 Oct 2022 Sanghyeok Lee, Minkyu Jeon, Injae Kim, Yunyang Xiong, Hyunwoo J. Kim

Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity.

Data Augmentation Image Classification

Deformable Graph Transformer

no code implementations29 Jun 2022 Jinyoung Park, Seongjun Yun, Hyeonjin Park, Jaewoo Kang, Jisu Jeong, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim

Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision.

Representation Learning

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection

1 code implementation CVPR 2022 Jihwan Park, Seungjun Lee, Hwan Heo, Hyeong Kyu Choi, Hyunwoo J. Kim

Motivated by various inference paths for HOI detection, we propose cross-path consistency learning (CPC), which is a novel end-to-end learning strategy to improve HOI detection for transformers by leveraging augmented decoding paths.

Human-Object Interaction Detection object-detection +1

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

1 code implementation CVPR 2022 Dohwan Ko, Joonmyung Choi, Juyeon Ko, Shinyeong Noh, Kyoung-Woon On, Eun-Sol Kim, Hyunwoo J. Kim

In this paper, we propose a novel multi-modal self-supervised framework Video-Text Temporally Weak Alignment-based Contrastive Learning (VT-TWINS) to capture significant information from noisy and weakly correlated data using a variant of Dynamic Time Warping (DTW).

Contrastive Learning Dynamic Time Warping +1

Metropolis-Hastings Data Augmentation for Graph Neural Networks

no code implementations NeurIPS 2021 Hyeonjin Park, Seunghun Lee, Sihyeon Kim, Jinyoung Park, Jisu Jeong, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim

We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.

Data Augmentation

Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones

4 code implementations5 Jan 2022 Chongkeun Paik, Hyunwoo J. Kim

In the second approach, although DeepSORT only processes a quarter of all frames due to hardware and time limitations, our model with DeepSORT (42. 9%) outperforms FairMOT (71. 4%) in terms of recall.

Association Disaster Response +3

Deformable Graph Convolutional Networks

no code implementations29 Dec 2021 Jinyoung Park, Sungdong Yoo, Jihwan Park, Hyunwoo J. Kim

To address the two common problems of graph convolution, in this paper, we propose Deformable Graph Convolutional Networks (Deformable GCNs) that adaptively perform convolution in multiple latent spaces and capture short/long-range dependencies between nodes.

Node Classification Representation Learning

Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs

1 code implementation11 Jun 2021 Seongjun Yun, Minbyul Jeong, Sungdong Yoo, Seunghun Lee, Sean S. Yi, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim

Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs.

Node Classification

HOTR: End-to-End Human-Object Interaction Detection with Transformers

1 code implementation CVPR 2021 Bumsoo Kim, Junhyun Lee, Jaewoo Kang, Eun-Sol Kim, Hyunwoo J. Kim

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i. e., humans) and target (i. e., objects) of interaction, and ii) the classification of the interaction labels.

Human-Object Interaction Detection object-detection +1

Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods

1 code implementation ECCV 2020 Byungjoo Kim, Bryce Chudomelka, Jinyoung Park, Jaewoo Kang, Youngjoon Hong, Hyunwoo J. Kim

Motivated by the SSP property and a generalized Runge-Kutta method, we propose Strong Stability Preserving networks (SSP networks) which improve robustness against adversarial attacks.

Unpaired Image Translation via Adaptive Convolution-based Normalization

no code implementations29 Nov 2019 Wonwoong Cho, Kangyeol Kim, Eungyeup Kim, Hyunwoo J. Kim, Jaegul Choo

Disentangling content and style information of an image has played an important role in recent success in image translation.

Translation

Graph Transformer Networks

1 code implementation NeurIPS 2019 Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim

In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion.

General Classification Link Prediction +2

ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification

no code implementations7 Apr 2019 Yunyang Xiong, Hyunwoo J. Kim, Varsha Hedau

It boosts the representational power by modeling, in a high dimensional space, interdependency of channels between a depthwise convolution layer and a projection layer in the ANTBlocks.

Classification General Classification +1

Efficient Relative Attribute Learning using Graph Neural Networks

1 code implementation ECCV 2018 Zihang Meng, Nagesh Adluru, Hyunwoo J. Kim, Glenn Fung, Vikas Singh

A sizable body of work on relative attributes provides compelling evidence that relating pairs of images along a continuum of strength pertaining to a visual attribute yields significant improvements in a wide variety of tasks in vision.

Tensorize, Factorize and Regularize: Robust Visual Relationship Learning

no code implementations CVPR 2018 Seong Jae Hwang, Sathya N. Ravi, Zirui Tao, Hyunwoo J. Kim, Maxwell D. Collins, Vikas Singh

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.

Relational Reasoning Visual Relationship Detection

Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families

no code implementations19 Apr 2018 Seong Jae Hwang, Ronak Mehta, Hyunwoo J. Kim, Vikas Singh

There has recently been a concerted effort to derive mechanisms in vision and machine learning systems to offer uncertainty estimates of the predictions they make.

Finding Differentially Covarying Needles in a Temporally Evolving Haystack: A Scan Statistics Perspective

no code implementations20 Nov 2017 Ronak Mehta, Hyunwoo J. Kim, Shulei Wang, Sterling C. Johnson, Ming Yuan, Vikas Singh

Recent results in coupled or temporal graphical models offer schemes for estimating the relationship structure between features when the data come from related (but distinct) longitudinal sources.

Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging

no code implementations CVPR 2017 Hyunwoo J. Kim, Nagesh Adluru, Heemanshu Suri, Baba C. Vemuri, Sterling C. Johnson, Vikas Singh

Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging.

Activity Recognition regression

Latent Variable Graphical Model Selection Using Harmonic Analysis: Applications to the Human Connectome Project (HCP)

no code implementations CVPR 2016 Won Hwa Kim, Hyunwoo J. Kim, Nagesh Adluru, Vikas Singh

A major goal of imaging studies such as the (ongoing) Human Connectome Project (HCP) is to characterize the structural network map of the human brain and identify its associations with covariates such as genotype, risk factors, and so on that correspond to an individual.

Model Selection

Interpolation on the Manifold of K Component GMMs

no code implementations ICCV 2015 Hyunwoo J. Kim, Nagesh Adluru, Monami Banerjee, Baba C. Vemuri, Vikas Singh

Probability density functions (PDFs) are fundamental "objects" in mathematics with numerous applications in computer vision, machine learning and medical imaging.

Cannot find the paper you are looking for? You can Submit a new open access paper.