RESEARCH

We are studying CNN-based object classification and detection robust to the environment changes such as illumination and pose changes

• Semantic Segmentation based on Semi-supervised learning

• Semantic Segmentation for Human Parsing

• Action Recognition using Self-supervised Learning

• Face Recognition using Convolutional Neural Network

• Binary Neural Network for Image Classification and Object Detection

We are studying deep learning network architectures for achieving better and best performances with less computational complexity

• Sequential Convolutional Residual Network for Image Recognition

• Active Weighted Mapping-based Residual Convolutional Neural Network

• Sequential Image-based Attention Network for Regression

We are studying Domain Adaptation and Disentangle methods for improving performances of deep learning methods without using a large size of training data and their corresponding ground truth

• Domain Adaptive Object Detection from RGB to Thermal Images

• Bridging Large Gap of Domain Spaces for Unsupervised Domain Adaptation

• Style and Content Disentangle with Autoencoder for classification

• Domain Adaptation-based Labeling the human between real and cartoon images

We are studying knowledge distillation methods for reducing the computational complexity of deep learning-based methods efficiently

• On-the-fly Network Role Change for Online Knowledge Distillation

• Knwoledge Distillation for 3D Object Detection

• Knowledge Distillation using Densely Guided Network

• Pacemaker Knowledge Distillation for On-the-fly Convolutional Neural Network