lab301 Blog

Thinking will not overcome fear but action will.

Non-local Neural Networks

Non-local NN

Posted by Blue on November 26, 2017

Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics

AdvDetect

Summary Two Types of Adversarial Example LBFGS-adversarials EA-adversarials A Hypothesis Explanation Test-set should be Interpolation of Train-set Ad...

Posted by zcy on November 26, 2017

Adversarial Inverse Graphics Networks

AIGN

Outline The paper proposes the Adversarial Inverse Graphics networks (AIGNs) for weakly supervised learning: Combining feedback from rendering predictions With distribution matching b...

Posted by Tab on November 26, 2017

Pixel Recurrent Neural Networks

RNN

#Outline [TOC] Introduction This is a work of Google DeepMind. It introduced a way to model the distribution of natural images for generative models. Two methods based on LSTM, Row-RNN and Diago...

Posted by Yan Zheyu on November 6, 2017

Single Shot MultiBox Detector

SSD

related work figure 1: classic network of object detection model figure 2: the confrontation between YOLO and SSD details Multi-scale feature maps for detection Convolutional predictors for de...

Posted by stephen zhou on November 4, 2017

Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks

P3D

Posted by Blue on November 4, 2017

Conditional Image Generation with PixelCNN Decoders

cPixelCNN

PixelRNN PixelRNNs generate new images pixel by pixel (and row by row) via LSTMs (or other RNNs). Each pixel is therefore conditioned on the previously generated pixels. Training of PixelRNN...

Posted by zcy on November 4, 2017

Generative Modeling of Audible Shapes for Object Perception

Generate Audio-Visual Data

Outline The paper proposes a a pipeline that generates audio-visual data based on their 3D object shapes and their physical properties: Construct a synthetic audio-visual dataset: Sound-2...

Posted by Tab on November 4, 2017

CVAE-GAN

Generative model

Introduction Present a general learning framework that combines a variational auto-encoder(VAE) with a generative adversarial network(GAN). Propose a new objective for the generator. Instead o...

Posted by Daxin on October 21, 2017

Deep Level Sets for Salient Object Detection

Salient Object Detection

Introduction This paper is written by Ping Hu, Bing Shuai, Jun Liu, Gang Wang and this report is done by Yan Zheyu from Liao’s Group in Zhejiang University. This paper uses Level Set method and int...

Posted by Ping Hu, Bing Shuai, Jun Liu, Gang Wang on October 19, 2017

FEATURED TAGS
machine learning generative model computer vision deep learning GAN VAE object detection Video Understanding Generative Model RNN Neural Networks Neural Network Image Synthesis
ABOUT ME

We're here to put a dent in the universe.

✉️ zcliao_lab@outlook.com

FRIENDS