Low-Light Image Enhancement with Adversarial Multi-Domain Transformer
We present a new multi-domain adversarial transformer for ISO domain transformation to improve the quality of low-light photographs.
Non-Local Image Formation Model for Photo Enhancement
We propose a new approach for pixel-wise image enhancement non-locally and a new metric for examining RGB color image quality.
Music-driven 3D Dance Motion Synthesis by Variational autoencoder
In this thesis, I applied a Variational Autoencoder (VAE), a deep generative model, to automatically generate more realistic and diverse dances from music.
Controllable Generation of Complex Graphic Layouts
We propose two methods for controllable generation of complex graphic layouts. The first method uses a pre-trained deep generative model to generate layouts that satisfy given constraints. The second method represents visual containment as a tree structure and generates web page layouts. Finally, we summarize design guidelines for controllable generation methods and discuss future directions.
Automatic Detection of Unstained Blood Cells in African Clawed Frogs using Machine Learning
Blood cell counting is an essential part of the study of blood cells and hematopoiesis. Conven- tional methods require Hematology and hematopoiesis requires a hematology analyzer, other experimental equipment, and staining with chemicals, which is a time-consuming process. In this study, we used an object detection algorithm, ”you only look once” (YOLO) to automatically identify and count the unstained blood cells of African clawed frogs. We changed the dataset used for training. We compared the performance of the model by changing and enhancing the data set used for training. The results showed that the original dataset augmented by randomly changing the brightness had the highest accuracy. However, the accuracy of discriminating be- tween leukocytes and thrombocytes did not reach a practical level regardless of which dataset was used for training. This is due to the fact that the ratio of leukocyte and plug cell labeled objects to red blood cells is too low.
A Step towards Artificial Pokemon Master
I introduced a novel multi-agent competition-based framework to train reinforcement learning agents to play Pokemon. Experiments showed that agents trained with out method outperformed those trained with self-play, even without reward shaping.
User-Guided Line Art Colorization with Generative Adversarial Networks
We proposed and experimented on multiple conditional Generative Adversarial Networks models for colorizing line art based on the given color hints by the user.
Reinforcement Learning for Automated Vehicle Operation in Simulation
We defined an interface (gyms environment) to SUMO so that modeling of automated driving can be done using inter-vehicle communication and reinforcement learning, and verified that the interface works by conducting reinforcement learning experiments.
Applyng WaveNet for the Generation of Rhythm Game Charts
WaveNet has achieved high accuracy in the Text-To-Speech task. We hypothesized and experimented that it may perform well in chart-generation task.
Using game information and learning strategies in reinforcement learning for NetHack
I applied reinforcement learning to NetHack in order to learn strategies. I proposed the model for this purpose and confirmed its effectiveness.
LoL-V2T: A Video-To-Text Dataset for Video Captioning in Esports
We introduced LoL-V2T: a large video-to-text dataset and generated captions for esports footage with deep learning.
Translating Illustration into Line Drawings by Supervised Learning
I worked on the experiment that the model would be able to generate line image of characters from its illustration automatically using deep learning. Adding to typical loss function, I used 'perceptual loss' to raise accuracy of the model.
Neural Networks for Airfoil Estimation and Their Web Interface
I developed Neural Networks for airfoil estimation, and the NN performed 1000x faster than conventional analysis. In addition, I developed web interface of the NN for airplane novices.