Search Results for author: Changick Kim

Found 61 papers, 23 papers with code

Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal

2 code implementations22 Apr 2019 Seungjun Jung, Muhammad Abul Hasan, Changick Kim

In this paper, we propose a novel algorithm to rectify illumination of the digitized documents by eliminating shading artifacts.

Document Shadow Removal

Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation

no code implementations1 Aug 2019 Jaehoon Choi, Minki Jeong, Taekyung Kim, Changick Kim

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation.

Clustering Semi-Supervised Image Classification +1

A Global-Local Emebdding Module for Fashion Landmark Detection

1 code implementation28 Aug 2019 Sumin Lee, Sungchan Oh, Chanho Jung, Changick Kim

To that end, in this paper, we propose a fashion landmark detection network with a global-local embedding module.

Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection

no code implementations ICCV 2019 Seunghyeon Kim, Jaehoon Choi, Taekyung Kim, Changick Kim

Experimental results show that our approach effectively improves the performance of the one-stage object detection in unsupervised domain adaptation setting.

Object object-detection +2

Why Does the VQA Model Answer No?: Improving Reasoning through Visual and Linguistic Inference

no code implementations25 Sep 2019 Seungjun Jung, Junyoung Byun, Kyujin Shim, Changick Kim

Moreover, by modifying the VQA model’s answer through the output of the NLI model, we show that VQA performance increases by 1. 1% from the original model.

Common Sense Reasoning Question Answering +1

RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation

no code implementations29 Sep 2019 Youngeun Kim, Seokeon Choi, Hankyeol Lee, Taekyung Kim, Changick Kim

In this paper, we introduce a self-supervised approach for video object segmentation without human labeled data. Specifically, we present Robust Pixel-level Matching Net-works (RPM-Net), a novel deep architecture that matches pixels between adjacent frames, using only color information from unlabeled videos for training.

Object Segmentation +3

Learning to Align Multi-Camera Domains using Part-Aware Clustering for Unsupervised Video Person Re-Identification

no code implementations29 Sep 2019 Youngeun Kim, Seokeon Choi, Taekyung Kim, Sumin Lee, Changick Kim

Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to apply the re-identification algorithm to a large camera network.

Clustering Metric Learning +2

BitNet: Learning-Based Bit-Depth Expansion

1 code implementation10 Oct 2019 Junyoung Byun, Kyujin Shim, Changick Kim

Since insufficient bit-depth may generate annoying false contours or lose detailed visual appearance, bit-depth expansion (BDE) from low bit-depth (LBD) images to high bit-depth (HBD) images becomes more and more important.

SSIM

SRG: Snippet Relatedness-based Temporal Action Proposal Generator

no code implementations26 Nov 2019 Hyunjun Eun, Sumin Lee, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim

Recent temporal action proposal generation approaches have suggested integrating segment- and snippet score-based methodologies to produce proposals with high recall and accurate boundaries.

Action Detection Temporal Action Proposal Generation

Learning to Discriminate Information for Online Action Detection

1 code implementation CVPR 2020 Hyunjun Eun, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim

For online action detection, in this paper, we propose a novel recurrent unit to explicitly discriminate the information relevant to an ongoing action from others.

Online Action Detection

Single-view 2D CNNs with Fully Automatic Non-nodule Categorization for False Positive Reduction in Pulmonary Nodule Detection

no code implementations9 Mar 2020 Hyunjun Eun, Daeyeong Kim, Chanho Jung, Changick Kim

Note that, instead of manual categorization requiring the heavy workload of radiologists, we propose to automatically categorize non-nodules based on the autoencoder and k-means clustering.

Clustering

Partial Domain Adaptation Using Graph Convolutional Networks

no code implementations16 May 2020 Seunghan Yang, Youngeun Kim, Dongki Jung, Changick Kim

Although existing partial domain adaptation methods effectively down-weigh outliers' importance, they do not consider data structure of each domain and do not directly align the feature distributions of the same class in the source and target domains, which may lead to misalignment of category-level distributions.

Partial Domain Adaptation

Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation

2 code implementations ECCV 2020 Taekyung Kim, Changick Kim

Finally, the exploration scheme locally aligns features in a class-wise manner complementary to the attraction scheme by selectively aligning unlabeled target features complementary to the perturbation scheme.

Semi-supervised Domain Adaptation Unsupervised Domain Adaptation

Arbitrary Style Transfer using Graph Instance Normalization

no code implementations6 Oct 2020 Dongki Jung, Seunghan Yang, Jaehoon Choi, Changick Kim

Style transfer is the image synthesis task, which applies a style of one image to another while preserving the content.

Domain Adaptation Image-to-Image Translation +2

SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction

1 code implementation6 Oct 2020 Jaehoon Choi, Dongki Jung, Donghwan Lee, Changick Kim

In this paper, we propose SAFENet that is designed to leverage semantic information to overcome the limitations of the photometric loss.

Depth Prediction Monocular Depth Estimation +1

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

1 code implementation CVPR 2021 Seokeon Choi, Taekyung Kim, Minki Jeong, Hyoungseob Park, Changick Kim

To this end, we combine learnable batch-instance normalization layers with meta-learning and investigate the challenging cases caused by both batch and instance normalization layers.

Data Augmentation Domain Generalization +2

Robust Federated Learning with Noisy Labels

1 code implementation3 Dec 2020 Seunghan Yang, Hyoungseob Park, Junyoung Byun, Changick Kim

To solve these problems, we introduce a novel federated learning scheme that the server cooperates with local models to maintain consistent decision boundaries by interchanging class-wise centroids.

Federated Learning Learning with noisy labels

Multi-view Arbitrary Style Transfer

no code implementations1 Jan 2021 Taekyung Kim, Changick Kim

We propose a photometric consistency loss, which directly enforces the geometrically consistent style texture across the view, and a stroke consistency loss, which matches the characteristics and directions of the brushstrokes by aligning the local patches of the corresponding pixels before minimizing feature deviation.

Style Transfer

Just a Few Points Are All You Need for Multi-View Stereo: A Novel Semi-Supervised Learning Method for Multi-View Stereo

no code implementations ICCV 2021 Taekyung Kim, Jaehoon Choi, Seokeon Choi, Dongki Jung, Changick Kim

We generate the spare ground truth of the DTU dataset for evaluation and extensive experiments verify that our SGT-MVSNet outperforms the state-of-the-art MVS methods on the sparse ground truth setting.

3D Reconstruction

On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks

no code implementations13 Jan 2021 Junyoung Byun, Hyojun Go, Changick Kim

In this paper, we pay attention to an implicit assumption of query-based black-box adversarial attacks that the target model's output exactly corresponds to the query input.

Few-shot Open-set Recognition by Transformation Consistency

1 code implementation CVPR 2021 Minki Jeong, Seokeon Choi, Changick Kim

Based on the transformation consistency, our method measures the difference between the transformed prototypes and a modified prototype set.

Few-Shot Learning Open Set Learning

Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training

no code implementations1 Apr 2021 Yoonhyung Kim, Changick Kim

In SSDA, a small number of labeled target images are given for training, and the effectiveness of those data is demonstrated by the previous studies.

Domain Adaptation Representation Learning +1

Improving Few-shot Learning with Weakly-supervised Object Localization

no code implementations25 May 2021 Inyong Koo, Minki Jeong, Changick Kim

In this work, we propose a novel framework that generates class representations by extracting features from class-relevant regions of the images.

Few-Shot Learning Metric Learning +1

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

no code implementations ICCV 2021 Dongki Jung, Jaehoon Choi, Yonghan Lee, Deokhwa Kim, Changick Kim, Dinesh Manocha, Donghwan Lee

We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments, e. g., a department store or a metro station.

3D Reconstruction Depth Estimation

Learning to Discriminate Information for Online Action Detection: Analysis and Application

no code implementations8 Sep 2021 Sumin Lee, Hyunjun Eun, Jinyoung Moon, Seokeon Choi, Yoonhyung Kim, Chanho Jung, Changick Kim

To overcome this problem, we propose a novel recurrent unit, named Information Discrimination Unit (IDU), which explicitly discriminates the information relevancy between an ongoing action and others to decide whether to accumulate the input information.

Action Anticipation Online Action Detection

Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation

no code implementations8 Nov 2021 Byeongjun Park, Taekyung Kim, Hyojun Go, Changick Kim

In this paper, we propose residual guidance loss that enables the depth estimation network to embed the discriminative feature by transferring the discriminability of auto-encoded features.

Monocular Depth Estimation Self-Supervised Learning

Geometrically Adaptive Dictionary Attack on Face Recognition

no code implementations8 Nov 2021 Junyoung Byun, Hyojun Go, Changick Kim

We apply the GADA strategy to two existing attack methods and show overwhelming performance improvement in the experiments on the LFW and CPLFW datasets.

3D Face Alignment Face Alignment +1

Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos

1 code implementation25 Jan 2022 Sangmin Woo, Jinyoung Park, Inyong Koo, Sumin Lee, Minki Jeong, Changick Kim

To our surprise, we found that training schedule shows divide-and-conquer-like pattern: time segments are first diversified regardless of the target, then coupled with each target, and fine-tuned to the target again.

Natural Language Queries Sentence +2

Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input

2 code implementations CVPR 2022 Junyoung Byun, Seungju Cho, Myung-Joon Kwon, Hee-Seon Kim, Changick Kim

To tackle this limitation, we propose the object-based diverse input (ODI) method that draws an adversarial image on a 3D object and induces the rendered image to be classified as the target class.

Face Verification Image Augmentation +1

Modality Mixer for Multi-modal Action Recognition

no code implementations24 Aug 2022 Sumin Lee, Sangmin Woo, Yeonju Park, Muhammad Adi Nugroho, Changick Kim

In multi-modal action recognition, it is important to consider not only the complementary nature of different modalities but also global action content.

Action Recognition

Temporal Flow Mask Attention for Open-Set Long-Tailed Recognition of Wild Animals in Camera-Trap Images

no code implementations31 Aug 2022 JeongSoo Kim, Sangmin Woo, Byeongjun Park, Changick Kim

Camera traps, unmanned observation devices, and deep learning-based image recognition systems have greatly reduced human effort in collecting and analyzing wildlife images.

Optical Flow Estimation

Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis

no code implementations15 Sep 2022 Byeongjun Park, Hyojun Go, Changick Kim

Although recent methods generate high-quality novel views, synthesizing with only one explicit or implicit 3D geometry has a trade-off between two objectives that we call the "seesaw" problem: 1) preserving reprojected contents and 2) completing realistic out-of-view regions.

Liveness score-based regression neural networks for face anti-spoofing

no code implementations19 Feb 2023 Youngjun Kwak, Minyoung Jung, Hunjae Yoo, JinHo Shin, Changick Kim

In this paper, we propose a liveness score-based regression network for overcoming the dependency on third party networks and users.

Face Anti-Spoofing regression

Sketch-based Video Object Localization

1 code implementation2 Apr 2023 Sangmin Woo, So-Yeong Jeon, Jinyoung Park, Minji Son, Sumin Lee, Changick Kim

We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch.

Object Object Localization +1

Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup

1 code implementation CVPR 2023 Junyoung Byun, Myung-Joon Kwon, Seungju Cho, Yoonji Kim, Changick Kim

Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications.

PG-RCNN: Semantic Surface Point Generation for 3D Object Detection

1 code implementation ICCV 2023 Inyong Koo, Inyoung Lee, Se-Ho Kim, Hee-Seon Kim, Woo-jin Jeon, Changick Kim

Motivated by this, we propose Point Generation R-CNN (PG-RCNN), a novel end-to-end detector that generates semantic surface points of foreground objects for accurate detection.

3D Object Detection object-detection +1

Audio-Visual Glance Network for Efficient Video Recognition

no code implementations ICCV 2023 Muhammad Adi Nugroho, Sangmin Woo, Sumin Lee, Changick Kim

To address this issue, we propose Audio-Visual Glance Network (AVGN), which leverages the commonly available audio and visual modalities to efficiently process the spatio-temporally important parts of a video.

Video Recognition Video Understanding

Denoising Task Routing for Diffusion Models

2 code implementations11 Oct 2023 Byeongjun Park, Sangmin Woo, Hyojun Go, Jin-Young Kim, Changick Kim

Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL).

Denoising Multi-Task Learning

Point-DynRF: Point-based Dynamic Radiance Fields from a Monocular Video

no code implementations14 Oct 2023 Byeongjun Park, Changick Kim

Dynamic radiance fields have emerged as a promising approach for generating novel views from a monocular video.

DiffRef3D: A Diffusion-based Proposal Refinement Framework for 3D Object Detection

no code implementations25 Oct 2023 Se-Ho Kim, Inyong Koo, Inyoung Lee, Byeongjun Park, Changick Kim

During training, DiffRef3D gradually adds noise to the residuals between proposals and target objects, then applies the noisy residuals to proposals to generate hypotheses.

3D Object Detection Denoising +2

Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models

no code implementations ICCV 2023 Hee-Seon Kim, Minji Son, Minbeom Kim, Myung-Joon Kwon, Changick Kim

To address this challenge, we introduce the Breaking Temporal Consistency (BTC) method, which is the first attempt to incorporate temporal information into video attacks using image models.

Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition

no code implementations21 Nov 2023 Sumin Lee, Sangmin Woo, Muhammad Adi Nugroho, Changick Kim

CFEM incorporates sepearte learnable query embeddings for each modality, which guide CFEM to extract complementary information and global action content from the other modalities.

Action Recognition

Class Incremental Learning for Adversarial Robustness

no code implementations6 Dec 2023 Seungju Cho, Hongsin Lee, Changick Kim

We observe that combining incremental learning with naive adversarial training easily leads to a loss of robustness.

Adversarial Robustness Class Incremental Learning +2

Indirect Gradient Matching for Adversarial Robust Distillation

no code implementations6 Dec 2023 Hongsin Lee, Seungju Cho, Changick Kim

In contrast to these approaches, we aim to transfer another piece of knowledge from the teacher, the input gradient.

Adversarial Robustness Data Augmentation

HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D

1 code implementation26 Dec 2023 Sangmin Woo, Byeongjun Park, Hyojun Go, Jin-Young Kim, Changick Kim

This work introduces HarmonyView, a simple yet effective diffusion sampling technique adept at decomposing two intricate aspects in single-image 3D generation: consistency and diversity.

Image to 3D

Towards Robust Multimodal Prompting With Missing Modalities

no code implementations26 Dec 2023 Jaehyuk Jang, Yooseung Wang, Changick Kim

Recently, multimodal prompting, which introduces learnable missing-aware prompts for all missing modality cases, has exhibited impressive performance.

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

1 code implementation14 Mar 2024 Byeongjun Park, Hyojun Go, Jin-Young Kim, Sangmin Woo, Seokil Ham, Changick Kim

To achieve this, we employ a sparse mixture-of-experts within each transformer block to utilize semantic information and facilitate handling conflicts in tasks through parameter isolation.

Denoising Multi-Task Learning

Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition

no code implementations21 Mar 2024 Sumin Lee, Yooseung Wang, Sangmin Woo, Changick Kim

Panoramic Activity Recognition (PAR) seeks to identify diverse human activities across different scales, from individual actions to social group and global activities in crowded panoramic scenes.

Activity Recognition

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