5 papers
Visual Tracking by TridentAlign and Context Embedding
Janghoon Choi, Junseok Kwon, Kyoung Mu Lee
Recent advances in Siamese network-based visual tracking methods have enabled high performance on numerous tracking benchmarks. However, extensive scale variations of the target ob…
Adaptive Regularization via Residual Smoothing in Deep Learning Optimization
Junghee Cho, Junseok Kwon, Byung-Woo Hong
We present an adaptive regularization algorithm that can be effectively applied to the optimization problem in deep learning framework. Our regularization algorithm aims to take in…
Deep ensemble network with explicit complementary model for accuracy-balanced classification
Dohyun Kim, Kyeorye Lee, Jiyeon Kim +2
The average accuracy is one of major evaluation metrics for classification systems, while the accuracy deviation is another important performance metric used to evaluate various de…
LED2Net: Deep Illumination-aware Dehazing with Low-light and Detail Enhancement
Guisik Kim, Junseok Kwon
We present a novel dehazing and low-light enhancement method based on an illumination map that is accurately estimated by a convolutional neural network (CNN). In this paper, the i…
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
Dong Wook Shu, Sung Woo Park, Junseok Kwon
In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-c…