32 citations · 107 across the 20 of their papers we have counts for
22 papers
Small Objects Matters in Weakly-supervised Semantic Segmentation
Cheolhyun Mun, Sanghuk Lee, Youngjung Uh +2
Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research comm…
Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations
Seogkyu Jeon, Bei Liu, Pilhyeon Lee +3
Training deep generative models usually requires a large amount of data. To alleviate the data collection cost, the task of zero-shot GAN adaptation aims to reuse well-trained gene…
AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks
Kibeom Hong, Seogkyu Jeon, Junsoo Lee +6
To deliver the artistic expression of the target style, recent studies exploit the attention mechanism owing to its ability to map the local patches of the style image to the corre…
Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection
Pilhyeon Lee, Taeoh Kim, Minho Shim +2
Temporal action detection aims to predict the time intervals and the classes of action instances in the video. Despite the promising performance, existing two-stream models exhibit…
Source-free Subject Adaptation for EEG-based Visual Recognition
Pilhyeon Lee, Seogkyu Jeon, Sunhee Hwang +2
This paper focuses on subject adaptation for EEG-based visual recognition. It aims at building a visual stimuli recognition system customized for the target subject whose EEG sampl…
BallGAN: 3D-aware Image Synthesis with a Spherical Background
Minjung Shin, Yunji Seo, Jeongmin Bae +4
3D-aware GANs aim to synthesize realistic 3D scenes such that they can be rendered in arbitrary perspectives to produce images. Although previous methods produce realistic images,…
Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
Sungpil Kho, Pilhyeon Lee, Wonyoung Lee +2
Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class predictions with only image-level labels for training. To this end, previous methods adopt the commo…
Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detection
Mirae Do, Seogkyu Jeon, Pilhyeon Lee +3
Domain adaptation for object detection (DAOD) has recently drawn much attention owing to its capability of detecting target objects without any annotations. To tackle the problem,…
Fair Contrastive Learning for Facial Attribute Classification
Sungho Park, Jewook Lee, Pilhyeon Lee +3
Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent suc…
Inter-subject Contrastive Learning for Subject Adaptive EEG-based Visual Recognition
Pilhyeon Lee, Sunhee Hwang, Jewook Lee +3
This paper tackles the problem of subject adaptive EEG-based visual recognition. Its goal is to accurately predict the categories of visual stimuli based on EEG signals with only a…
Subject Adaptive EEG-based Visual Recognition
Pilhyeon Lee, Sunhee Hwang, Seogkyu Jeon +1
This paper focuses on EEG-based visual recognition, aiming to predict the visual object class observed by a subject based on his/her EEG signals. One of the main challenges is the…
Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization
Seogkyu Jeon, Kibeom Hong, Pilhyeon Lee +2
Domain generalization aims to enhance the model robustness against domain shift without accessing the target domain. Since the available source domains for training are limited, re…
Domain-Aware Universal Style Transfer
Kibeom Hong, Seogkyu Jeon, Huan Yang +2
Style transfer aims to reproduce content images with the styles from reference images. Existing universal style transfer methods successfully deliver arbitrary styles to original i…
Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization
Pilhyeon Lee, Hyeran Byun
We tackle the problem of localizing temporal intervals of actions with only a single frame label for each action instance for training. Owing to label sparsity, existing work fails…
Continuous Face Aging Generative Adversarial Networks
Seogkyu Jeon, Pilhyeon Lee, Kibeom Hong +1
Face aging is the task aiming to translate the faces in input images to designated ages. To simplify the problem, previous methods have limited themselves only able to produce disc…
ArrowGAN : Learning to Generate Videos by Learning Arrow of Time
Kibeom Hong, Youngjung Uh, Hyeran Byun
Training GANs on videos is even more sophisticated than on images because videos have a distinguished dimension: time. While recent methods designed a dedicated architecture consid…
FairFaceGAN: Fairness-aware Facial Image-to-Image Translation
Sunhee Hwang, Sungho Park, Dohyung Kim +2
In this paper, we introduce FairFaceGAN, a fairness-aware facial Image-to-Image translation model, mitigating the problem of unwanted translation in protected attributes (e.g., gen…
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localization
Minsong Ki, Youngjung Uh, Wonyoung Lee +1
Weakly supervised object localization (WSOL) aims to localize the target object using only the image-level supervision. Recent methods encourage the model to activate feature maps…
README: REpresentation learning by fairness-Aware Disentangling MEthod
Sungho Park, Dohyung Kim, Sunhee Hwang +1
Fair representation learning aims to encode invariant representation with respect to the protected attribute, such as gender or age. In this paper, we design Fairness-aware Disenta…
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
Pilhyeon Lee, Jinglu Wang, Yan Lu +1
Weakly-supervised temporal action localization aims to learn detecting temporal intervals of action classes with only video-level labels. To this end, it is crucial to separate fra…
Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
Myeongjin Kim, Hyeran Byun
Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic do…
Background Suppression Network for Weakly-supervised Temporal Action Localization
Pilhyeon Lee, Youngjung Uh, Hyeran Byun
Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels…