lab301 Blog

Thinking will not overcome fear but action will.

Associative Embedding

joint detection and grouping

Related work Vector embeddings Perceptual organization group pixels into parts detecting basic visual units first and grouping them second. our approach performs detection and grouping ...

PixelGAN autoencoders

GAN

Outline The paper proposes a generative autoencoder combining PixelCNN & GAN: Show different priors result in different decompositions of information A categorical prior can be us...

Interpretable Convolutional Neural Network

Reference Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu. Interpretable Convolutional Neural Networks, arxiv 2017.

Feature Pyramid Networks for Object Detection

Abstract This paper deals with the issue of Object Detection, and the author provide a new algorithm call “Feature Pyramid Networks” , which is inspired by “Image Pyramid” in traditional object de...

VAE Tutorial

VAE

Formation Maximum Likelihood — Find $\theta$ to maximize $P(X)$, where $X$ is the data. $z \sim P(z)$, which we can sample from Naive solution Approximate with samples of z Problems Need ...

Globally and Locally Consistent Image Completion

inpainting

Related work diffusion-based image synthesis: histograms of local features patch-based approaches: PatchMatch CNN-based: limited to very small and thin masks context encoder-bas...

Unsupervised representation learning with deep convolutional generative adversarial networks

DCGAN

Related work Unsupervised representation learning: K-means auto-encoders Generating natural images: parametric and non- parametric non-parametric: texture synthesis , super-resolution, in-painting...

Auto-Encoding Variational Bayes

VAE

Introduction This paper is written by Diederik P. Kingma, Max Welling and this report is done by Yan Zheyu from Liao’s Group in Zhejiang University. Because the writer of paper Tutorial on Variatio...

Generative Adversarial Networks

GAN

Outline Abstract Related Works Main idea Discussion Abstract Generative Adversarial Networks is a new framework for estimating generative models via an adversarial process, which inclu...

Deep Bilateral Learning for real-time image enhancement(Siggraph 2017)

Outline Bilateral Grid Local Affine Transformation Network FrameWork Bilateral Grid Bilateral Grid Bilateral Grid Bilateral Grid Bilateral Grid Bilateral Grid...