Search Results for author: Euntai Kim

Found 12 papers, 8 papers with code

SHUNIT: Style Harmonization for Unpaired Image-to-Image Translation

1 code implementation11 Jan 2023 Seokbeom Song, Suhyeon Lee, Hongje Seong, Kyoungwon Min, Euntai Kim

Our SHUNIT generates a new style by harmonizing the target domain style retrieved from a class memory and an original source image style.

Image-to-Image Translation Object +1

Revisiting Self-Similarity: Structural Embedding for Image Retrieval

1 code implementation CVPR 2023 Seongwon Lee, Suhyeon Lee, Hongje Seong, Euntai Kim

Despite advances in global image representation, existing image retrieval approaches rarely consider geometric structure during the global retrieval stage.

Image Retrieval Retrieval

Domain Adaptive Video Semantic Segmentation via Cross-Domain Moving Object Mixing

1 code implementation4 Nov 2022 Kyusik Cho, Suhyeon Lee, Hongje Seong, Euntai Kim

Since the ground truth label on the target domain is unavailable during training, the bias problem leads to skewed predictions, forgetting to predict hard-to-transfer classes.

Domain Adaptation Semantic Segmentation +1

One-Trimap Video Matting

1 code implementation27 Jul 2022 Hongje Seong, Seoung Wug Oh, Brian Price, Euntai Kim, Joon-Young Lee

A key of OTVM is the joint modeling of trimap propagation and alpha prediction.

Image Matting Video Matting

WildNet: Learning Domain Generalized Semantic Segmentation from the Wild

1 code implementation CVPR 2022 Suhyeon Lee, Hongje Seong, Seongwon Lee, Euntai Kim

To this end, we diversify styles by augmenting source features to resemble wild styles and enable networks to adapt to a variety of styles.

Domain Generalization Semantic Segmentation

Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier

no code implementations23 Dec 2021 Youngjo Lee, Hongje Seong, Euntai Kim

We believe that we can select a better reference frame to achieve the better UVOS performance than using only the first frame or the entire video as a reference frame.

Object Semantic Segmentation +2

Hierarchical Memory Matching Network for Video Object Segmentation

1 code implementation ICCV 2021 Hongje Seong, Seoung Wug Oh, Joon-Young Lee, Seongwon Lee, Suhyeon Lee, Euntai Kim

Based on a recent memory-based method [33], we propose two advanced memory read modules that enable us to perform memory reading in multiple scales while exploiting temporal smoothness.

Object Retrieval +3

Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer

no code implementations23 Dec 2020 Suhyeon Lee, Junhyuk Hyun, Hongje Seong, Euntai Kim

The main problem of UDA for semantic segmentation relies on reducing the domain gap between the real image and synthetic image.

Segmentation Semantic Segmentation +1

Kernelized Memory Network for Video Object Segmentation

1 code implementation ECCV 2020 Hongje Seong, Junhyuk Hyun, Euntai Kim

Unlike in previous works, we use the Hide-and-Seek strategy in pre-training to obtain the best possible results in handling occlusions and segment boundary extraction.

Object Semantic Segmentation +2

FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition

no code implementations17 Jul 2019 Hongje Seong, Junhyuk Hyun, Euntai Kim

Scene recognition is an image recognition problem aimed at predicting the category of the place at which the image is taken.

Scene Recognition

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