67 citations · 235 across the 15 of their papers we have counts for
15 papers
Masking meets Supervision: A Strong Learning Alliance
Byeongho Heo, Taekyung Kim, Sangdoo Yun +1
Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentati…
What Do Self-Supervised Vision Transformers Learn?
Namuk Park, Wonjae Kim, Byeongho Heo +2
We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks…
Panoramic Image-to-Image Translation
Soohyun Kim, Junho Kim, Taekyung Kim +4
In this paper, we tackle the challenging task of Panoramic Image-to-Image translation (Pano-I2I) for the first time. This task is difficult due to the geometric distortion of panor…
Robust Camera Pose Refinement for Multi-Resolution Hash Encoding
Hwan Heo, Taekyung Kim, Jiyoung Lee +4
Multi-resolution hash encoding has recently been proposed to reduce the computational cost of neural renderings, such as NeRF. This method requires accurate camera poses for the ne…
Self-Supervised 3D Traversability Estimation with Proxy Bank Guidance
Jihwan Bae, Junwon Seo, Taekyung Kim +3
Traversability estimation for mobile robots in off-road environments requires more than conventional semantic segmentation used in constrained environments like on-road conditions.…
Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation
Byeongjun Park, Taekyung Kim, Hyojun Go +1
Photometric consistency loss is one of the representative objective functions commonly used for self-supervised monocular depth estimation. However, this loss often causes unstable…
Meta Batch-Instance Normalization for Generalizable Person Re-Identification
Seokeon Choi, Taekyung Kim, Minki Jeong +2
Although supervised person re-identification (Re-ID) methods have shown impressive performance, they suffer from a poor generalization capability on unseen domains. Therefore, gene…
Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
Taekyung Kim, Changick Kim
Although unsupervised domain adaptation methods have been widely adopted across several computer vision tasks, it is more desirable if we can exploit a few labeled data from new do…
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
Seokeon Choi, Sumin Lee, Youngeun Kim +2
Visible-infrared person re-identification (VI-ReID) is an important task in night-time surveillance applications, since visible cameras are difficult to capture valid appearance in…
RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation
Youngeun Kim, Seokeon Choi, Hankyeol Lee +2
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-…
CNN-based Semantic Segmentation using Level Set Loss
Youngeun Kim, Seunghyeon Kim, Taekyung Kim +1
Thesedays, Convolutional Neural Networks are widely used in semantic segmentation. However, since CNN-based segmentation networks produce low-resolution outputs with rich semantic…
Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
Seunghyeon Kim, Jaehoon Choi, Taekyung Kim +1
Deep learning-based object detectors have shown remarkable improvements. However, supervised learning-based methods perform poorly when the train data and the test data have differ…
Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
Jaehoon Choi, Taekyung Kim, Changick Kim
Deep learning-based semantic segmentation methods have an intrinsic limitation that training a model requires a large amount of data with pixel-level annotations. To address this c…
Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
Jaehoon Choi, Minki Jeong, Taekyung Kim +1
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-la…
Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
Taekyung Kim, Minki Jeong, Seunghyeon Kim +2
We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-…