lab301 Blog

Thinking will not overcome fear but action will.

Visualizing And Understanding Recurrent Networks

VisRNN

Summary Background Recurrent Neural Networks (RNNs),and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide r...

A Recurrent Neural Network For Image Generation

DRAW

Outline As the figure shows, the way of generating images is an iterative method. It is a much reasonable approach particularly when we need to generate a large image. Besides, one of i...

Characterizing and Improving Stability in Neural Style Transfer

Stable Video Color Transfer

Outline This is a work of L.Fei-fei’s group, which was admitted in the ICCV17. It extends some ideas of perceptual loss and style transfer based on feed-forward network to video style ...

RoomNet End-to-End Room Layout Estimation

Room Layout Estimation

Introduction Room Layout Estimation from a monocular image, which aims to delineate a 2D boxy representation of an indoor scene, is an essential step for a wide variety of computer vision tasks....

Neural Color Transfer between Images

Neural Color Transfer

Outline Related Work Here, we further discuss some details of the paper “Visual Attribute Transfer through Deep Image Analogy”. Considering that this paper got some ideas from it, ...

Learning to Segment Every Thing

weight transfer

mask rcnn architecture training Stage-wise training: First stage: train a Faster R-CNN Second stage: train mask head and weight transfer with box head fixed End-to-end joint training: J...

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

HighResImgCGAN

Summary

Adversarial Image Perturbation for Privacy Protection, A Game Theory Perspective

AIP

#Outline [TOC] Introduction This is a work of Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany. It introduced a game between users who use Adversarial Ima...

Stack GAN++ Realistic Image Synthesis with Stacked Generative Adversarial Networks

Reference Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2017). StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks. arXiv pr...

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Super-Resolution

Introduction Super-Resolution is a task of estimating a high-resolution image from its low-resolution counterpart, which is a ill-posed problem. Many supervised SR algorithms recently proposed u...