1 code implementation • 11 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.
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.
1 code implementation • 4 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.
1 code implementation • 27 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.
2 code implementations • CVPR 2022 • Seongwon Lee, Hongje Seong, Suhyeon Lee, Euntai Kim
Geometric verification is considered a de facto solution for the re-ranking task in image retrieval.
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.
no code implementations • 23 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.
Ranked #6 on Unsupervised Video Object Segmentation on FBMS test
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.
no code implementations • 23 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.
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.
no code implementations • 26 Jul 2019 • Junhyuk Hyun, Hongje Seong, Euntai Kim
Pooling is one of the main elements in convolutional neural networks.
no code implementations • 17 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.
Ranked #1 on Scene Recognition on MIT Indoor Scenes