no code implementations • 18 Sep 2017 • Sanghyun Woo, Soonmin Hwang, In So Kweon
One-stage object detectors such as SSD or YOLO already have shown promising accuracy with small memory footprint and fast speed.
10 code implementations • 17 Jul 2018 • Jongchan Park, Sanghyun Woo, Joon-Young Lee, In So Kweon
In this work, we focus on the effect of attention in general deep neural networks.
31 code implementations • ECCV 2018 • Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon
We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks.
3 code implementations • NeurIPS 2018 • Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
In this paper, we present a method that improves scene graph generation by explicitly modeling inter-dependency among the entire object instances.
1 code implementation • 24 Nov 2018 • Yunjae Jung, Donghyeon Cho, Dahun Kim, Sanghyun Woo, In So Kweon
The proposed variance loss allows a network to predict output scores for each frame with high discrepancy which enables effective feature learning and significantly improves model performance.
Ranked #2 on Unsupervised Video Summarization on SumMe
Supervised Video Summarization Unsupervised Video Summarization
2 code implementations • CVPR 2019 • Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
Video inpainting aims to fill spatio-temporal holes with plausible content in a video.
Ranked #7 on Video Inpainting on DAVIS
1 code implementation • CVPR 2019 • Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
Blind video decaptioning is a problem of automatically removing text overlays and inpainting the occluded parts in videos without any input masks.
no code implementations • 30 May 2019 • Sanghyun Woo, Dahun Kim, KwanYong Park, Joon-Young Lee, In So Kweon
Our video inpainting network consists of two stages.
no code implementations • 30 Jul 2019 • Ho-Deok Jang, Sanghyun Woo, Philipp Benz, Jinsun Park, In So Kweon
We present a simple yet effective prediction module for a one-stage detector.
no code implementations • 21 Aug 2019 • Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
In this paper, we investigate the problem of unpaired video-to-video translation.
no code implementations • 3 Feb 2020 • Yunjae Jung, Dahun Kim, Sanghyun Woo, Kyung-Su Kim, Sungjin Kim, In So Kweon
In this paper, we propose to explicitly learn to imagine a storyline that bridges the visual gap.
Ranked #7 on Visual Storytelling on VIST
1 code implementation • CVPR 2020 • Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
In this paper, we propose and explore a new video extension of this task, called video panoptic segmentation.
Ranked #7 on Video Panoptic Segmentation on Cityscapes-VPS (using extra training data)
no code implementations • 26 Nov 2020 • Myungchul Kim, Sanghyun Woo, Dahun Kim, In So Kweon
In this work, we propose Boundary Basis based Instance Segmentation(B2Inst) to learn a global boundary representation that can complement existing global-mask-based methods that are often lacking high-frequency details.
no code implementations • ECCV 2020 • Inkyu Shin, Sanghyun Woo, Fei Pan, Inso Kweon
However, since only the confident predictions are taken as pseudo labels, existing self-training approaches inevitably produce sparse pseudo labels in practice.
no code implementations • CVPR 2021 • Sanghyun Woo, Dahun Kim, Joon-Young Lee, In So Kweon
Temporal correspondence - linking pixels or objects across frames - is a fundamental supervisory signal for the video models.
Ranked #6 on Video Panoptic Segmentation on Cityscapes-VPS (using extra training data)
no code implementations • 23 Jul 2021 • Inkyu Shin, KwanYong Park, Sanghyun Woo, In So Kweon
In this work, we present a new video extension of this task, namely Unsupervised Domain Adaptation for Video Semantic Segmentation.
no code implementations • ICCV 2021 • Inkyu Shin, Dong-Jin Kim, Jae Won Cho, Sanghyun Woo, KwanYong Park, In So Kweon
In order to find the uncertain points, we generate an inconsistency mask using the proposed adaptive pixel selector and we label these segment-based regions to achieve near supervised performance with only a small fraction (about 2. 2%) ground truth points, which we call "Segment based Pixel-Labeling (SPL)".
no code implementations • 2 Sep 2021 • Adrit Rao, Jongchan Park, Sanghyun Woo, Joon-Young Lee, Oliver Aalami
The use of computer vision to automate the classification of medical images is widely studied.
no code implementations • NeurIPS 2020 • KwanYong Park, Sanghyun Woo, Inkyu Shin, In So Kweon
The scheme first clusters compound target data based on style, discovering multiple latent domains (discover).
1 code implementation • CVPR 2022 • KwanYong Park, Sanghyun Woo, Seoung Wug Oh, In So Kweon, Joon-Young Lee
In this per-clip inference scheme, we update the memory with an interval and simultaneously process a set of consecutive frames (i. e. clip) between the memory updates.
no code implementations • 16 Dec 2022 • Junha Song, KwanYong Park, Inkyu Shin, Sanghyun Woo, Chaoning Zhang, In So Kweon
In addition, to prevent overfitting of the TTA model, we devise novel regularization which modulates the adaptation rates using domain-similarity between the source and the current target domain.
no code implementations • 16 Dec 2022 • Sungsu Hur, Inkyu Shin, KwanYong Park, Sanghyun Woo, In So Kweon
To successfully train our framework, we collect the partial, confident target samples that are classified as known or unknown through on our proposed multi-criteria selection.
no code implementations • 20 Dec 2022 • Sanghyun Woo, KwanYong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee
The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames.
no code implementations • 20 Dec 2022 • Sanghyun Woo, KwanYong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee
First, no tracking supervisions are in LVIS, which leads to inconsistent learning of detection (with LVIS and TAO) and tracking (only with TAO).
no code implementations • CVPR 2023 • KwanYong Park, Sanghyun Woo, Seoung Wug Oh, In So Kweon, Joon-Young Lee
Mask-guided matting has shown great practicality compared to traditional trimap-based methods.
10 code implementations • CVPR 2023 • Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie
This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation.
Ranked #45 on Semantic Segmentation on ADE20K
no code implementations • 17 Mar 2023 • Daehan Kim, Minseok Seo, KwanYong Park, Inkyu Shin, Sanghyun Woo, In-So Kweon, Dong-Geol Choi
In specific, we achieve domain mixup in two-step: cut and paste.
no code implementations • 29 Feb 2024 • Hoon Kim, Minje Jang, Wonjun Yoon, Jisoo Lee, Donghyun Na, Sanghyun Woo
We introduce a co-designed approach for human portrait relighting that combines a physics-guided architecture with a pre-training framework.
no code implementations • ECCV 2020 • Yunjae Jung, Donghyeon Cho, Sanghyun Woo, In So Kweon
In order to summarize a content video properly, it is important to grasp the sequential structure of video as well as the long-term dependency between frames.