297 citations · 325 across the 12 of their papers we have counts for
14 papers
Weight-based Mask for Domain Adaptation
Eunseop Lee, Inhan Kim, Daijin Kim
In computer vision, unsupervised domain adaptation (UDA) is an approach to transferring knowledge from a label-rich source domain to a fully-unlabeled target domain. Conventional U…
Object Discovery via Contrastive Learning for Weakly Supervised Object Detection
Jinhwan Seo, Wonho Bae, Danica J. Sutherland +2
Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit…
Revisiting Image Pyramid Structure for High Resolution Salient Object Detection
Taehun Kim, Kunhee Kim, Joonyeong Lee +3
Salient object detection (SOD) has been in the spotlight recently, yet has been studied less for high-resolution (HR) images. Unfortunately, HR images and their pixel-level annotat…
DAM-GAN : Image Inpainting using Dynamic Attention Map based on Fake Texture Detection
Dongmin Cha, Daijin Kim
Deep neural advancements have recently brought remarkable image synthesis performance to the field of image inpainting. The adaptation of generative adversarial networks (GAN) in p…
FA-GAN: Feature-Aware GAN for Text to Image Synthesis
Eunyeong Jeon, Kunhee Kim, Daijin Kim
Text-to-image synthesis aims to generate a photo-realistic image from a given natural language description. Previous works have made significant progress with Generative Adversaria…
Localization Uncertainty-Based Attention for Object Detection
Sanghun Park, Kunhee Kim, Eunseop Lee +1
Object detection has been applied in a wide variety of real world scenarios, so detection algorithms must provide confidence in the results to ensure that appropriate decisions can…
UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation
Taehun Kim, Hyemin Lee, Daijin Kim
We propose Uncertainty Augmented Context Attention network (UACANet) for polyp segmentation which consider a uncertain area of the saliency map. We construct a modified version of…
SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation
Taehun Kim, Jinseong Kim, Daijin Kim
Semantic segmentation networks adopt transfer learning from image classification networks which occurs a shortage of spatial context information. For this reason, we propose Spatia…
Detector With Focus: Normalizing Gradient In Image Pyramid
Yonghyun Kim, Bong-Nam Kang, Daijin Kim
An image pyramid can extend many object detection algorithms to solve detection on multiple scales. However, interpolation during the resampling process of an image pyramid causes…
Attentional Feature-Pair Relation Networks for Accurate Face Recognition
Bong-Nam Kang, Yonghyun Kim, Bongjin Jun +1
Human face recognition is one of the most important research areas in biometrics. However, the robust face recognition under a drastic change of the facial pose, expression, and il…
Pairwise Relational Networks using Local Appearance Features for Face Recognition
Bong-Nam Kang, Yonghyun Kim, Daijin Kim
We propose a new face recognition method, called a pairwise relational network (PRN), which takes local appearance features around landmark points on the feature map, and captures…
BAN: Focusing on Boundary Context for Object Detection
Yonghyun Kim, Taewook Kim, Bong-Nam Kang +2
Visual context is one of the important clue for object detection and the context information for boundaries of an object is especially valuable. We propose a boundary aware network…
Pairwise Relational Networks for Face Recognition
Bong-Nam Kang, Yonghyun Kim, Daijin Kim
Existing face recognition using deep neural networks is difficult to know what kind of features are used to discriminate the identities of face images clearly. To investigate the e…
SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection
Yonghyun Kim, Bong-Nam Kang, Daijin Kim
Most of the recent successful methods in accurate object detection build on the convolutional neural networks (CNN). However, due to the lack of scale normalization in CNN-based de…