Search Results - "Hong, Seunghoon"

Learning Deconvolution Network for Semantic Segmentation by Noh, Hyeonwoo, Hong, Seunghoon, Han, Bohyung

“…We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted…”
Get full text

Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis by Hong, Seunghoon, Yang, Dingdong, Choi, Jongwook, Lee, Honglak

“…We propose a novel hierarchical approach for text-to-image synthesis by inferring semantic layout. Instead of learning a direct mapping from text to image, our…”
Get full text

Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network by Seunghoon Hong, Junhyuk Oh, Honglak Lee, Bohyung Han

“…We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised…”
Get full text

Weakly Supervised Semantic Segmentation Using Web-Crawled Videos by Seunghoon Hong, Donghun Yeo, Suha Kwak, Honglak Lee, Bohyung Han

“…We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly…”
Get full text

Joint Image Clustering and Labeling by Matrix Factorization by Seunghoon Hong, Jonghyun Choi, Feyereisl, Jan, Bohyung Han, Davis, Larry S.

“…We propose a novel algorithm to cluster and annotate a set of input images jointly, where the images are clustered into several discriminative groups and each…”
Get full text

Orderless Tracking through Model-Averaged Posterior Estimation by Hong, Seunghoon, Kwak, Suha, Han, Bohyung

“…We propose a novel offline tracking algorithm based on model-averaged posterior estimation through patch matching across frames. Contrary to existing online…”
Get full text

Joint Segmentation and Pose Tracking of Human in Natural Videos by Lim, Taegyu, Hong, Seunghoon, Han, Bohyung, Han, Joon Hee

“…We propose an on-line algorithm to extract a human by foreground/background segmentation and estimate pose of the human from the videos captured by moving…”
Get full text

Part-based Pseudo Label Refinement for Unsupervised Person Re-identification by Cho, Yoonki, Kim, Woo Jae, Hong, Seunghoon, Yoon, Sung-Eui

“…Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques…”
Get full text

Personalized Image Aesthetic Quality Assessment by Joint Regression and Ranking by Kayoung Park, Seunghoon Hong, Mooyeol Baek, Bohyung Han

“…We propose an image aesthetic quality assessment algorithm, which considers personal taste in addition to generally perceived preference. This problem is…”
Get full text

Improving Unsupervised Image Clustering With Robust Learning by Park, Sungwon, Han, Sungwon, Kim, Sundong, Kim, Danu, Park, Sungkyu, Hong, Seunghoon, Cha, Meeyoung

“…Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and…”
Get full text

SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data by Kim, Jinwoo, Yoo, Jaehoon, Lee, Juho, Hong, Seunghoon

“…Generative modeling of set-structured data, such as point clouds, requires reasoning over local and global structures at various scales. However, adopting…”
Get full text

Adversarial Defense via Learning to Generate Diverse Attacks by Jang, Yunseok, Zhao, Tianchen, Hong, Seunghoon, Lee, Honglak

“…With the remarkable success of deep learning, Deep Neural Networks (DNNs) have been applied as dominant tools to various machine learning domains. Despite this…”
Get full text

Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution by Kim, Jaechang, Lee, Yunjoo, Hong, Seunghoon, Ok, Jungseul

“…Audio super resolution aims to predict the missing high resolution components of the low resolution audio signals. While audio in nature is a continuous…”
Get full text

Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers by Yoo, Jaehoon, Kim, Semin, Lee, Doyup, Kim, Chiheon, Hong, Seunghoon

“…Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the longterm…”
Get full text

Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks by Kim, Woo Jae, Hong, Seunghoon, Yoon, Sung-Eui

“…Adversarial attacks with improved transferability -the ability of an adversarial example crafted on a known model to also fool unknown models -have recently…”
Get full text

Neural Contrast Enhancement of CT Image by Seo, Minkyo, Kim, Dongkeun, Lee, Kyungmoon, Hong, Seunghoon, Bae, Jae Seok, Hoon Kim, Jung, Kwak, Suha

“…Contrast materials are often injected into body to contrast specific tissues in Computed Tomography (CT) images. Contrast Enhanced CT (CECT) images obtained in…”
Get full text

Feature Augmentation based Test-Time Adaptation by Cho, Younggeol, Kim, Youngrae, Yoon, Junho, Hong, Seunghoon, Lee, Dongman

“…Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA…”
Get full text

Revisiting Random Walks for Learning on Graphs by Kim, Jinwoo, Zaghen, Olga, Suleymanzade, Ayhan, Ryou, Youngmin, Hong, Seunghoon

“…We revisit a simple idea for machine learning on graphs, where a random walk on a graph produces a machine-readable record, and this record is processed by a…”
Get full text

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality by Jung, Whie, Yoo, Jaehoon, Ahn, Sungjin, Hong, Seunghoon

“…Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual…”
Get full text

Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild by Kim, Donggyun, Cho, Seongwoong, Kim, Semin, Luo, Chong, Hong, Seunghoon

“…Large language models have evolved data-efficient generalists, benefiting from the universal language interface and large-scale pre-training. However,…”
Get full text