1 code implementation • 25 Apr 2024 • Gahyeon Kim, Sohee Kim, Seokju Lee
Through our experiments, we have identified important issues in CoOp and CoCoOp: the context learned through traditional image augmentation is biased toward seen classes, negatively impacting generalization to unseen classes.
no code implementations • 13 Feb 2024 • Yunji Jung, Seokju Lee, Tair Djanibekov, Hyunjung Shim, Jong Chul Ye
In this work, we propose a training-free approach for non-rigid editing with Stable Diffusion, aimed at improving the identity preservation quality without compromising editability.
no code implementations • 5 Feb 2024 • Dunam Kim, Seokju Lee
Recent studies on generalizing CLIP for monocular depth estimation reveal that CLIP pre-trained on web-crawled data is inefficient for deriving proper similarities between image patches and depth-related prompts.
no code implementations • 21 Sep 2023 • Fei Pan, Xu Yin, Seokju Lee, Axi Niu, SungEui Yoon, In So Kweon
Then, we propose a semantic mining module that takes the object masks to refine the pseudo labels in the target domain.
no code implementations • 19 Jul 2022 • Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim, In So Kweon
Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains.
no code implementations • ICCV 2021 • Seokju Lee, Francois Rameau, Fei Pan, In So Kweon
Experiments on KITTI, Cityscapes, and Waymo Open Dataset demonstrate the relevance of our approach and show that our method outperforms state-of-the-art algorithms for the tasks of self-supervised monocular depth estimation, object motion segmentation, monocular scene flow estimation, and visual odometry.
1 code implementation • 12 Aug 2021 • Antyanta Bangunharcana, Jae Won Cho, Seokju Lee, In So Kweon, Kyung-Soo Kim, Soohyun Kim
Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions.
2 code implementations • 1 Mar 2021 • Ukcheol Shin, Kyunghyun Lee, Seokju Lee, In So Kweon
Based on the proposed module, the photometric consistency loss can provide complementary self-supervision to networks.
1 code implementation • 4 Feb 2021 • Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision.
Ranked #2 on Monocular Depth Estimation on Cityscapes
1 code implementation • 23 Oct 2020 • Chaoning Zhang, Philipp Benz, Dawit Mureja Argaw, Seokju Lee, Junsik Kim, Francois Rameau, Jean-Charles Bazin, In So Kweon
ResNet or DenseNet?
1 code implementation • CVPR 2020 • Fei Pan, Inkyu Shin, Francois Rameau, Seokju Lee, In So Kweon
Finally, to decrease the intra-domain gap, we propose to employ a self-supervised adaptation technique from the easy to the hard split.
Ranked #2 on Domain Adaptation on Synscapes-to-Cityscapes
1 code implementation • 19 Dec 2019 • Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision.
no code implementations • 16 Sep 2019 • Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
Based on rigid projective geometry, the estimated stereo depth is used to guide the camera motion estimation, and the depth and camera motion are used to guide the residual flow estimation.
no code implementations • 16 Sep 2019 • Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon
We postulate that success on this task requires the network to learn semantic and geometric knowledge in the ego-centric view.
1 code implementation • CVPR 2019 • Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon
We take an approach to learn a generalizable embedding space for novel tasks.
no code implementations • 5 Dec 2017 • Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon
Recent advances in visual recognition show overarching success by virtue of large amounts of supervised data.
3 code implementations • ICCV 2017 • Seokju Lee, Junsik Kim, Jae Shin Yoon, Seunghak Shin, Oleksandr Bailo, Namil Kim, Tae-Hee Lee, Hyun Seok Hong, Seung-Hoon Han, In So Kweon
In this paper, we propose a unified end-to-end trainable multi-task network that jointly handles lane and road marking detection and recognition that is guided by a vanishing point under adverse weather conditions.
Ranked #1 on Lane Detection on Caltech Lanes Washington
no code implementations • ICCV 2017 • Jae Shin Yoon, Francois Rameau, Junsik Kim, Seokju Lee, Seunghak Shin, In So Kweon
We propose a novel video object segmentation algorithm based on pixel-level matching using Convolutional Neural Networks (CNN).
Ranked #73 on Semi-Supervised Video Object Segmentation on DAVIS 2016