Search Results for author: Sanghyun Woo

Found 29 papers, 9 papers with code

StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection

no code implementations18 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.

BAM: Bottleneck Attention Module

10 code implementations17 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.

Neural Architecture Search

CBAM: Convolutional Block Attention Module

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.

General Classification Image Classification

LinkNet: Relational Embedding for Scene Graph

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.

Graph Generation Scene Graph Generation

Discriminative Feature Learning for Unsupervised Video Summarization

1 code implementation24 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.

Supervised Video Summarization Unsupervised Video Summarization

Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence

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.

Video Denoising Video Inpainting +1

Propose-and-Attend Single Shot Detector

no code implementations30 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.

Video Panoptic Segmentation

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)

Instance Segmentation Segmentation +5

The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation

no code implementations26 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.

Instance Segmentation Scene Understanding +2

Two-phase Pseudo Label Densification for Self-training based Domain Adaptation

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.

Pseudo Label Unsupervised Domain Adaptation +1

Learning to Associate Every Segment for Video Panoptic Segmentation

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)

Video Panoptic Segmentation

Unsupervised Domain Adaptation for Video Semantic Segmentation

no code implementations23 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.

Semantic Segmentation Unsupervised Domain Adaptation +1

LabOR: Labeling Only if Required for Domain Adaptive 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)".

Semantic Segmentation Unsupervised Domain Adaptation

Studying the Effects of Self-Attention for Medical Image Analysis

no code implementations2 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.

Per-Clip Video Object Segmentation

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.

Object Segmentation +3

Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management

no code implementations16 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.

Denoising Image Classification +4

Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation

no code implementations16 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.

Universal Domain Adaptation

Tracking by Associating Clips

no code implementations20 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.

Chunking Management +2

Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection

no code implementations20 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).

Video Object Detection

ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

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.

Object Detection Representation Learning +2

SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting

no code implementations29 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.

Global-and-Local Relative Position Embedding for Unsupervised Video Summarization

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.

Computational Efficiency Position +1

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