Home

Paper Link: http://www.visionlab.cs.hku.hk/publications/wliu_aaai18.pdf Contributions simple and efficient Char-Net for distorted scene text recognition. This network can be trained in end-to-end using only text images and their corresponding character labels. Hierarchical Attention Mechanism (HAM) that facilitates the rectification of in...

최근 해외 트래픽(트위터, 넷플릭스, 유튜브, 깃헙 등등) 사용 시 느려지는 문제를 해결하기 위해서 1.1.1.1 warp를 사용하시는 분들이 많습니다. 그런데 아직 1.1.1.1은 스마트폰에서만 지원하기 때문에 PC에서는 1.1.1.1을 사용을 못하고 계실텐데 최근에 사용할 수 있는 방법을 찾게되어 이를 알려드립니다. 과정은 다음과 같습니다. wireguard를 설치합니다. (https://www.wireguard.com/install/) 여기에서 OS에 맞게 설치하시면 됩니다. wgcf를 다운로드 합니다. (https://github.com/ViRb3/wgcf/releases) 윈도우 64비트의 경...

Paper Link: https://arxiv.org/abs/1901.03003 Overview A Multi-Object Rectified Attention Network for Scene Text Recognition (MORAN) can read rotated, scaled and stretched characters. MORAN = multi-object rectification network (MORN) + attention-based sequence recognition network (ASRN) MORN: works to rectify image. weakly super...

Paper Link: https://arxiv.org/abs/1912.10205 Decoupled Attention Network (DAN) What is the difference? In traditional attention mechanism, alignment is coupled with decoding. They conduct alignment operation using visual information and historical decoding information. Traditional attention mechanism often ha...

Image-to-Image Translation with Conditional Adversarial Networks arxiv paper link First general purpose conditional GAN for image to image translation task Impressive output on inpainting, future state prediction, image manipulation guided by user constraints, style transfer, super-resolution Method U-net based a...

Basic Deep Learning Concepts Hard concepts are Bolded Supervised Learning / Unsupervised Learning / semi-supervised, weakly-supervised weight initialization learning rate decay dropout forward propagation(inference) / backward propagation Activation What is activation layer and why use it ReLU, Leaky ReLU softmax sigmoid...

Paper arxiv link: Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network Efficient Sub-Pixel Convolutional neural Network (ESPCN) Figure 1. The proposed efficient sub-pixel convolutional neural network (ESPCN), with two convolution layers for feature maps extraction, and a sub-pixel convol...

Deformable Convolutional Networks Paper arxiv link Deformable Convolution Standard convolution has fixed sampling location and receptive field. To solve this problem, Deformable convolution use learnable offset. 2D Convolution The standard 2D convolution consists of two steps: 1) sampling using a regular grid \(\mathcal{R}\) over the input ...