Loading [MathJax]/extensions/MathZoom.js
In So Kweon - IEEE Xplore Author Profile
Access provided by:

MIT Libraries

Sign Out
Access provided by:

MIT Libraries

Sign Out
ADVANCED SEARCH

Author details

< Back

In So Kweon

Also published under: Inso Kweon, In-So Kweon, I. S. Kweon, In so Kweon, In-so Kweon

Publications
277
Citations
10,234
Publications by Year
20012024
Co-Authors:
Show All Co-Authors (262)
Image of author In So Kweon

In So Kweon

Also published under: Inso Kweon, In-So Kweon, I. S. Kweon, In so Kweon, In-so Kweon

Affiliation

KAIST

Publication Topics

Biography

In So Kweon (Member, IEEE) received the B.S. and M.S. degrees in mechanical design and production engineering from Seoul National University, South Korea, in 1981 and 1983, respectively, and the Ph.D. degree in robotics from the Robotics Institute, Carnegie Mellon University, in 1990. He is currently a Professor of electrical engineering (EE) and the Director of the National Core Research Center—P3 DigiCar Center, KAIST. He has served as the Department Head of automation and design engineering (ADE) at KAIST from 1995 to 1998. His research interests include computer vision and robotics. He has coauthored several books, including Metric Invariants for Camera Calibration, and more than 300 technical papers. He is a member of many computer vis...
Publications
277
Citations
10,234
Publications by Year
20012024
Co-Authors:
Show All Co-Authors (262)
Author's Published Works

Showing 1-25 of 277 results

  • Sort

Filter Results

Show

Sort By

Results

MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation

Fei Pan;Xu Yin;Seokju Lee;Axi Niu;Sungeui Yoon;In So Kweon

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Year: 2024 | Conference Paper |
Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain contains unlabeled video frames. Drawing upon recent advancements of self-supervised learning of the object motion from unlabeled videos with geometric constraint,...Show More

MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation

Fei Pan;Xu Yin;Seokju Lee;Axi Niu;Sungeui Yoon;In So Kweon

Year: 2024 | Conference Paper |

Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data

Dong-Jin Kim;Tae-Hyun Oh;Jinsoo Choi;In So Kweon

IEEE Access
Year: 2024 | Volume: 12 | Journal Article |
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is expensive in terms of labor, time, and cost. In contrast to manually annotating all the training samples, separately collecting uni-modal datasets is immensely easier, e.g., a large-scale image dataset and a sentence da...Show More

Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data

Dong-Jin Kim;Tae-Hyun Oh;Jinsoo Choi;In So Kweon

Year: 2024 | Volume: 12 | Journal Article |

ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution

Axi Niu;Trung X. Pham;Kang Zhang;Jinqiu Sun;Yu Zhu;Qingsen Yan;In So Kweon;Yanning Zhang

IEEE Transactions on Broadcasting
Year: 2024 | Volume: 70, Issue: 2 | Journal Article |
Cited by: Papers (5)
Diffusion models have gained significant popularity for image-to-image translation tasks. Previous efforts applying diffusion models to image super-resolution have demonstrated that iteratively refining pure Gaussian noise using a U-Net architecture trained on denoising at various noise levels can yield satisfactory high-resolution images from low-resolution inputs. However, this iterative refinem...Show More

ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution

Axi Niu;Trung X. Pham;Kang Zhang;Jinqiu Sun;Yu Zhu;Qingsen Yan;In So Kweon;Yanning Zhang

Year: 2024 | Volume: 70, Issue: 2 | Journal Article |

Redundant-Coded Masked Grid Pattern for Full-Sky Star Identification

Jiawen Liao;Xin Wei;Axi Niu;Yanning Zhang;In So Kweon;Chun Qi

IEEE Transactions on Aerospace and Electronic Systems
Year: 2024 | Volume: 60, Issue: 4 | Journal Article |
Cited by: Papers (1)
Full-sky autonomous star identification is one of the key technologies in the research on star sensors. As one of the classical pattern-based star identification methods, the grid algorithm has shown promising performance. Na further modified it to improve its robustness to position noise. However, the inherent alignment star mismatch and pattern inconsistency are still not solved. To address thes...Show More

Redundant-Coded Masked Grid Pattern for Full-Sky Star Identification

Jiawen Liao;Xin Wei;Axi Niu;Yanning Zhang;In So Kweon;Chun Qi

Year: 2024 | Volume: 60, Issue: 4 | Journal Article |

Learning from Multi-Perception Features for Real-Word Image Super-resolution

Axi Niu;Kang Zhang;Trung X. Pham;Pei Wang;Jinqiu Sun;In So Kweon;Yanning Zhang

IEEE Transactions on Circuits and Systems for Video Technology
Year: 2024 | Early Access Article |
Cited by: Papers (2)
Actual image super-resolution is an extremely challenging task due to complex degradations existing in the image. To solve this problem, two dominant methodologies have emerged: degradation-estimation-based Addressing actual image super-resolution remains a formidable challenge due to the intricate degradations present in images. Two primary methodologies have emerged: degradation-estimation-based...Show More

Learning from Multi-Perception Features for Real-Word Image Super-resolution

Axi Niu;Kang Zhang;Trung X. Pham;Pei Wang;Jinqiu Sun;In So Kweon;Yanning Zhang

Year: 2024 | Early Access Article |

CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution

Axi Niu;Kang Zhang;Trung X. Pham;Jinqiu Sun;Yu Zhu;In So Kweon;Yanning Zhang

2023 IEEE International Conference on Image Processing (ICIP)
Year: 2023 | Conference Paper |
Cited by: Papers (9)
Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM to image super-resolution (SR) have shown that iteratively refining a pure Gaussian noise with a conditional image using a U-Net trained on denoising at various-level noises can help obtain a satisfied high-resolution image for the low-reso...Show More

CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution

Axi Niu;Kang Zhang;Trung X. Pham;Jinqiu Sun;Yu Zhu;In So Kweon;Yanning Zhang

Year: 2023 | Conference Paper |

Test-Time Adaptation in the Dynamic World With Compound Domain Knowledge Management

Junha Song;Kwanyong Park;InKyu Shin;Sanghyun Woo;Chaoning Zhang;In So Kweon

IEEE Robotics and Automation Letters
Year: 2023 | Volume: 8, Issue: 11 | Journal Article |
Cited by: Papers (2)
Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and improve its performance during test time (i.e., lifelong adaptation). Several works for TTA have shown promising adaptation performances in continuously changing env...Show More

Test-Time Adaptation in the Dynamic World With Compound Domain Knowledge Management

Junha Song;Kwanyong Park;InKyu Shin;Sanghyun Woo;Chaoning Zhang;In So Kweon

Year: 2023 | Volume: 8, Issue: 11 | Journal Article |

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee;Jonathan Tremblay;Valts Blukis;Bowen Wen;Byeong-Uk Lee;Inkyu Shin;Stan Birchfield;In So Kweon;Kuk-Jin Yoon

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
Cited by: Papers (11)
Test-time adaptation methods have been gaining attention recently as a practical solution for addressing source-to-target domain gaps by gradually updating the model without requiring labels on the target data. In this paper, we propose a method of test-time adaptation for category-level object pose estimation called TTA-COPE. We design a pose ensemble approach with a self-training loss using pose...Show More

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee;Jonathan Tremblay;Valts Blukis;Bowen Wen;Byeong-Uk Lee;Inkyu Shin;Stan Birchfield;In So Kweon;Kuk-Jin Yoon

Year: 2023 | Conference Paper |

Single View Scene Scale Estimation using Scale Field

Byeong-Uk Lee;Jianming Zhang;Yannick Hold-Geoffroy;In So Kweon

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
In this paper, we propose a single image scale estimation method based on a novel scale field representation. A scale field defines the local pixel-to-metric conversion ratio along the gravity direction on all the ground pixels. This representation resolves the ambiguity in camera parameters, allowing us to use a simple yet effective way to collect scale annotations on arbitrary images from human ...Show More

Single View Scene Scale Estimation using Scale Field

Byeong-Uk Lee;Jianming Zhang;Yannick Hold-Geoffroy;In So Kweon

Year: 2023 | Conference Paper |

Deep Depth Estimation from Thermal Image

Ukcheol Shin;Jinsun Park;In So Kweon

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
Cited by: Papers (19)
Robust and accurate geometric understanding against adverse weather conditions is one top prioritized conditions to achieve a high-level autonomy of self-driving cars. However, autonomous driving algorithms relying on the visible spectrum band are easily impacted by weather and lighting conditions. A long-wave infrared camera, also known as a thermal imaging camera, is a potential rescue to achiev...Show More

Deep Depth Estimation from Thermal Image

Ukcheol Shin;Jinsun Park;In So Kweon

Year: 2023 | Conference Paper |

Mask-Guided Matting in the Wild

Kwanyong Park;Sanghyun Woo;Seoung Wug Oh;In So Kweon;Joon-Young Lee

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
Cited by: Papers (5)
Mask-guided matting has shown great practicality compared to traditional trimap-based methods. The mask-guided approach takes an easily-obtainable coarse mask as guidance and produces an accurate alpha matte. To extend the success toward practical usage, we tackle mask-guided matting in the wild, which covers a wide range of categories in their complex context robustly. To this end, we propose a s...Show More

Mask-Guided Matting in the Wild

Kwanyong Park;Sanghyun Woo;Seoung Wug Oh;In So Kweon;Joon-Young Lee

Year: 2023 | Conference Paper |

Generative Bias for Robust Visual Question Answering

Jae Won Cho;Dong-Jin Kim;Hyeonggon Ryu;In So Kweon

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
Cited by: Papers (26)
The task of Visual Question Answering (VQA) is known to be plagued by the issue of VQA models exploiting biases within the dataset to make its final prediction. Various previous ensemble based debiasing methods have been proposed where an additional model is purposefully trained to be biased in order to train a robust target model. However, these methods compute the bias for a model simply from th...Show More

Generative Bias for Robust Visual Question Answering

Jae Won Cho;Dong-Jin Kim;Hyeonggon Ryu;In So Kweon

Year: 2023 | Conference Paper |

EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization

Junha Song;Jungsoo Lee;In So Kweon;Sungha Choi

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
Cited by: Papers (23)
This paper presents a simple yet effective approach that improves continual test-time adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge devices with limited memory, so reducing memory is crucial but has been overlooked in previous TTA studies. In addition, long-term adaptation often leads to catastrophic forgetting and error accumulation, which hinders applying ...Show More

EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization

Junha Song;Jungsoo Lee;In So Kweon;Sungha Choi

Year: 2023 | Conference Paper |

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

Sanghyun Woo;Shoubhik Debnath;Ronghang Hu;Xinlei Chen;Zhuang Liu;In So Kweon;Saining Xie

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
Cited by: Papers (361)
Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt [33], have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they ...Show More

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

Sanghyun Woo;Shoubhik Debnath;Ronghang Hu;Xinlei Chen;Zhuang Liu;In So Kweon;Saining Xie

Year: 2023 | Conference Paper |

Counterfactual Mix-Up for Visual Question Answering

Jae Won Cho;Dong-Jin Kim;Yunjae Jung;In So Kweon

IEEE Access
Year: 2023 | Volume: 11 | Journal Article |
Cited by: Papers (2)
Counterfactuals have been shown to be a powerful method in Visual Question Answering in the alleviation of Visual Question Answering’s unimodal bias. However, existing counterfactual methods tend to generate samples that are not diverse or require auxiliary models to synthesize additional data. In this regard, we propose a more diverse and simple counterfactual sample synthesis method called Count...Show More

Counterfactual Mix-Up for Visual Question Answering

Jae Won Cho;Dong-Jin Kim;Yunjae Jung;In So Kweon

Year: 2023 | Volume: 11 | Journal Article |

Self-Sufficient Framework for Continuous Sign Language Recognition

Youngjoon Jang;Youngtaek Oh;Jae Won Cho;Myungchul Kim;Dong-Jin Kim;In So Kweon;Joon Son Chung

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2023 | Conference Paper |
Cited by: Papers (9)
The goal of this work is to develop self-sufficient framework for Continuous Sign Language Recognition (CSLR) that addresses key issues of sign language recognition. These include the need for complex multi-scale features such as hands, face, and mouth for understanding, and absence of frame-level annotations. To this end, we propose (1) Divide and Focus Convolution (DFConv) which extracts both ma...Show More

Self-Sufficient Framework for Continuous Sign Language Recognition

Youngjoon Jang;Youngtaek Oh;Jae Won Cho;Myungchul Kim;Dong-Jin Kim;In So Kweon;Joon Son Chung

Year: 2023 | Conference Paper |

Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation

Sungsu Hur;Inkyu Shin;Kwanyong Park;Sanghyun Woo;In So Kweon

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Year: 2023 | Conference Paper |
Cited by: Papers (6)
Universal Domain Adaptation aims to transfer the knowledge between the datasets by handling two shifts: domain-shift and category-shift. The main challenge is correctly distinguishing the unknown target samples while adapting the distribution of known class knowledge from source to target. Most existing methods approach this problem by first training the target adapted known classifier and then re...Show More

Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation

Sungsu Hur;Inkyu Shin;Kwanyong Park;Sanghyun Woo;In So Kweon

Year: 2023 | Conference Paper |

Event-Specific Audio-Visual Fusion Layers: A Simple and New Perspective on Video Understanding

Arda Senocak;Junsik Kim;Tae-Hyun Oh;Dingzeyu Li;In So Kweon

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Year: 2023 | Conference Paper |
Cited by: Papers (5)
To understand our surrounding world, our brain is continuously inundated with multisensory information and their complex interactions coming from the outside world at any given moment. While processing this information might seem effortless for human brains, it is challenging to build a machine that can perform similar tasks since complex interactions cannot be dealt with a single type of integrat...Show More

Event-Specific Audio-Visual Fusion Layers: A Simple and New Perspective on Video Understanding

Arda Senocak;Junsik Kim;Tae-Hyun Oh;Dingzeyu Li;In So Kweon

Year: 2023 | Conference Paper |

Self-supervised Monocular Depth Estimation from Thermal Images via Adversarial Multi-spectral Adaptation

Ukcheol Shin;Kwanyong Park;Byeong-Uk Lee;Kyunghyun Lee;In So Kweon

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Year: 2023 | Conference Paper |
Cited by: Papers (14)
Recently, thermal image based 3D understanding is gradually attracting attention for an illumination condition agnostic machine vision. However, the difficulty of the thermal image lies in insufficient training supervision due to its low-contrast and texturesless properties. Also, introducing additional modality requires further constraints such as complicated multi-sensor calibration and synchron...Show More

Self-supervised Monocular Depth Estimation from Thermal Images via Adversarial Multi-spectral Adaptation

Ukcheol Shin;Kwanyong Park;Byeong-Uk Lee;Kyunghyun Lee;In So Kweon

Year: 2023 | Conference Paper |

MCDAL: Maximum Classifier Discrepancy for Active Learning

Jae Won Cho;Dong-Jin Kim;Yunjae Jung;In So Kweon

IEEE Transactions on Neural Networks and Learning Systems
Year: 2023 | Volume: 34, Issue: 11 | Journal Article |
Cited by: Papers (26)
Recent state-of-the-art active learning methods have mostly leveraged generative adversarial networks (GANs) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyperparameters. In contrast to these methods, in this article, we propose a novel active learning framework that we call Maximum Classifier Discrepancy for Active Learning (MCDAL) that takes...Show More

MCDAL: Maximum Classifier Discrepancy for Active Learning

Jae Won Cho;Dong-Jin Kim;Yunjae Jung;In So Kweon

Year: 2023 | Volume: 34, Issue: 11 | Journal Article |

A Large-Scale Virtual Dataset and Egocentric Localization for Disaster Responses

Hae-Gon Jeon;Sunghoon Im;Byeong-Uk Lee;François Rameau;Dong-Geol Choi;Jean Oh;In So Kweon;Martial Hebert

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2023 | Volume: 45, Issue: 6 | Journal Article |
Cited by: Papers (6)
With the increasing social demands of disaster response, methods of visual observation for rescue and safety have become increasingly important. However, because of the shortage of datasets for disaster scenarios, there has been little progress in computer vision and robotics in this field. With this in mind, we present the first large-scale synthetic dataset of egocentric viewpoints for disaster ...Show More

A Large-Scale Virtual Dataset and Egocentric Localization for Disaster Responses

Hae-Gon Jeon;Sunghoon Im;Byeong-Uk Lee;François Rameau;Dong-Geol Choi;Jean Oh;In So Kweon;Martial Hebert

Year: 2023 | Volume: 45, Issue: 6 | Journal Article |

DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning

Ukcheol Shin;Kyunghyun Lee;In So Kweon

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Year: 2022 | Conference Paper |
Cited by: Papers (1)
In this paper, we propose a multi-objective camera ISP framework that utilizes Deep Reinforcement Learning (DRL) and camera ISP toolbox that consist of network-based and conventional ISP tools. The proposed DRL-based camera ISP framework iteratively selects a proper tool from the toolbox and applies it to the image to maximize a given vision task-specific reward function. For this purpose, we impl...Show More

DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning

Ukcheol Shin;Kyunghyun Lee;In So Kweon

Year: 2022 | Conference Paper |

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Inkyu Shin;Yi-Hsuan Tsai;Bingbing Zhuang;Samuel Schulter;Buyu Liu;Sparsh Garg;In So Kweon;Kuk-Jin Yoon

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2022 | Conference Paper |
Cited by: Papers (28)
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semantic segmentation. We find that, directly applying existing methods usually results in performance instability at test time, because multi-modal input is...Show More

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Inkyu Shin;Yi-Hsuan Tsai;Bingbing Zhuang;Samuel Schulter;Buyu Liu;Sparsh Garg;In So Kweon;Kuk-Jin Yoon

Year: 2022 | Conference Paper |

Per-Clip Video Object Segmentation

Kwanyong Park;Sanghyun Woo;Seoung Wug Oh;In So Kweon;Joon-Young Lee

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2022 | Conference Paper |
Cited by: Papers (29)
Recently, memory-based approaches show promising results on semi-supervised video object segmentation. These methods predict object masks frame-by-frame with the help of frequently updated memory of the previous mask. Different from this per-frame inference, we investigate an alternative perspective by treating video object segmentation as clip-wise mask propagation. In this per-clip inference sch...Show More

Per-Clip Video Object Segmentation

Kwanyong Park;Sanghyun Woo;Seoung Wug Oh;In So Kweon;Joon-Young Lee

Year: 2022 | Conference Paper |

DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning

Youngtaek Oh;Dong-Jin Kim;In So Kweon

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2022 | Conference Paper |
Cited by: Papers (49)
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the sem...Show More

DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning

Youngtaek Oh;Dong-Jin Kim;In So Kweon

Year: 2022 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.