Search Results - "Suha Kwak"

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

The feasibility of deep learning-based synthetic contrast-enhanced CT from nonenhanced CT in emergency department patients with acute abdominal pain by Kim, Se Woo, Kim, Jung Hoon, Kwak, Suha, Seo, Minkyo, Ryoo, Changhyun, Shin, Cheong-Il, Jang, Siwon, Cho, Jungheum, Kim, Young-Hoon, Jeon, Kyutae

“…Our objective was to investigate the feasibility of deep learning-based synthetic contrast-enhanced CT (DL-SCE-CT) from nonenhanced CT (NECT) in patients who…”
Get full text

Unsupervised Object Discovery and Tracking in Video Collections by Kwak, Suha, Minsu Cho, Laptev, Ivan, Ponce, Jean, Schmid, Cordelia

“…This paper addresses the problem of automatically localizing dominant objects as spatio-temporal tubes in a noisy collection of videos with minimal or even no…”
Get full text

Deep Metric Learning Beyond Binary Supervision by Kim, Sungyeon, Seo, Minkyo, Laptev, Ivan, Cho, Minsu, Kwak, Suha

“…Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not. Such a binary…”
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

On-Line Video Event Detection by Constraint Flow by Kwak, Suha, Han, Bohyung, Han, Joon Hee

“…We present a novel approach in describing and detecting the composite video events based on scenarios, which constrain the configurations of target events by…”
Get full text

Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation by Ahn, Jiwoon, Kwak, Suha

“…The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework…”
Get full text

Learning occlusion with likelihoods for visual tracking by Suha Kwak, Woonhyun Nam, Bohyung Han, Joon Hee Han

“…We propose a novel algorithm to detect occlusion for visual tracking through learning with observation likelihoods. In our technique, target is divided into…”
Get full text

Generalized background subtraction based on hybrid inference by belief propagation and Bayesian filtering by Suha Kwak, Taegyu Lim, Woonhyun Nam, Bohyung Han, Joon Hee Han

“…We propose a novel background subtraction algorithm for the videos captured by a moving camera. In our technique, foreground and background appearance models…”
Get full text

Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations by Ahn, Jiwoon, Cho, Sunghyun, Kwak, Suha

“…This paper presents a novel approach for learning instance segmentation with image-level class labels as supervision. Our approach generates pseudo instance…”
Get full text

Semi-supervised Semantic Segmentation with Error Localization Network by Kwon, Donghyeon, Kwak, Suha

“…This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others…”
Get full text

Scenario-based video event recognition by constraint flow by Suha Kwak, Bohyung Han, Joon Hee Han

“…We present a novel approach to representing and recognizing composite video events. A composite event is specified by a scenario, which is based on primitive…”
Get full text

Proxy Anchor Loss for Deep Metric Learning by Kim, Sungyeon, Kim, Dongwon, Cho, Minsu, Kwak, Suha

“…Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic…”
Get full text

ReSTR: Convolution-free Referring Image Segmentation Using Transformers by Kim, Namyup, Kim, Dongwon, Kwak, Suha, Lan, Cuiling, Zeng, Wenjun

“…Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of…”
Get full text

Domain-Specific Batch Normalization for Unsupervised Domain Adaptation by Chang, Woong-Gi, You, Tackgeun, Seo, Seonguk, Kwak, Suha, Han, Bohyung

“…We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both…”
Get full text

Learning to Detect Semantic Boundaries with Image-Level Class Labels by Kim, Namyup, Hwang, Sehyun, Kwak, Suha

“…This paper presents the first attempt to learn semantic boundary detection using image-level class labels as supervision. Our method starts by estimating…”
Get full text

Style Neophile: Constantly Seeking Novel Styles for Domain Generalization by Kang, Juwon, Lee, Sohyun, Kim, Namyup, Kwak, Suha

“…This paper studies domain generalization via domain-invariant representation learning. Existing methods in this direction suppose that a domain can be…”
Get full text

Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals by Minsu Cho, Kwak, Suha, Schmid, Cordelia, Ponce, Jean

“…This paper addresses unsupervised discovery and localization of dominant objects from a noisy image collection with multiple object classes. The setting of…”
Get full text

Improving Cross-Modal Retrieval with Set of Diverse Embeddings by Kim, Dongwon, Kim, Namyup, Kwak, Suha

“…Cross-modal retrieval across image and text modalities is a challenging task due to its inherent ambiguity: An image often exhibits various situations, and a…”
Get full text

FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation by Lee, Sohyun, Son, Taeyoung, Kwak, Suha

“…Robust visual recognition under adverse weather conditions is of great importance in real-world applications. In this context, we propose a new method for…”
Get full text