Hyeonwoo Noh

DeconvNet. DeconvNet : Learning Deconvolution Network for Semantic Segmentation

caffe. modified version of caffe which support DeconvNet and DecoupledNet

DPPnet. DPPnet: Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction

DecoupledNet. DecoupledNet: Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

vqa_task_discovery. Transfer Learning via Unsupervised Task Discovery for Visual Question Answering

voc_classification. Python

VQA-Transfer-ExternalData. Transfer Learning via Unsupervised Task Discovery for Visual Question Answering

my_ubuntu_settings. Vim Script

RAU_VQA. Training Recurrent Answering Units with Joint Loss Minimization for VQA

VQABrowser. Qualitative / quantitative evaluation tool for Visual Question Answering dataset.

HyeonwooNoh.github.io. HTML

rl-starter-files. RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code

ViZDoomDeterministic. C++

Gumbel-Softmax-VAE-in-tensorflow. Semi-Supervised Learning with Categorical VAE (experimented on MNIST)