Topic Tag: image

home Forums Topic Tag: image

 Analysis of supervised and semi-supervised GrowCut applied to segmentation of masses in mammography images

 

Breast cancer is already one of the most common form of cancer worldwide. Mammography image analysis is still the most effective diagnostic method to promote the early detection of breast cancer. Accurately segmenting tumors in digital mammography images is important to improve diagnosis capabiliti…


 Multi-shot Pedestrian Re-identification via Sequential Decision Making

   

Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we pr…


 Tacotron 2: Generating Human-like Speech from Text

     

Posted by Jonathan Shen and Ruoming Pang, Software Engineers, on behalf of the Google Brain and Machine Perception Teams Generating very natural sounding speech from text (text-to-speech, TTS) has been a research goal for decades. There has been great progress in TTS research over the last few year…


 DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer

   

We have witnessed rapid evolution of deep neural network architecture design in the past years. These latest progresses greatly facilitate the developments in various areas such as computer vision and natural language processing. However, along with the extraordinary performance, these state-of-the…


 Automated flow for compressing convolution neural networks for efficient edge-computation with FPGA

 

Deep convolutional neural networks (CNN) based solutions are the current state- of-the-art for computer vision tasks. Due to the large size of these models, they are typically run on clusters of CPUs or GPUs. However, power requirements and cost budgets can be a major hindrance in adoption of CNN f…


 “Zero-Shot” Super-Resolution using Deep Internal Learning

  

Deep Learning has led to a dramatic leap in Super-Resolution (SR) performance in the past few years. However, being supervised, these SR methods are restricted to specific training data, where the acquisition of the low-resolution (LR) images from their high-resolution (HR) counterparts is predeter…


 A Summary of the First Conference on Robot Learning

 

Posted by Vincent Vanhoucke, Principal Scientist, Google Brain Team and Melanie Saldaña, Program Manager, University Relations Whether in the form of autonomous vehicles, home assistants or disaster rescue units, robotic systems of the future will need to be able to operate safely and effectively …


 Introducing Appsperiments: Exploring the Potentials of Mobile Photography

  

Posted by Alex Kauffmann, Interaction Researcher, Google Research Each of the world’s approximately two billion smartphone owners is carrying a camera capable of capturing photos and video of a tonal richness and quality unimaginable even five years ago. Until recently, those cameras behaved …


 Introduction To Neural Networks Part 2 – A Worked Example

 

This tutorial was originally posted here on Ben’s blog, GormAnalysis. The purpose of this article is to hold your hand through the process of designing and training a neural network. Note that this article is Part 2 of Introduction to Neural Networks. R code for this tutorial is provided…


 Feature Visualization

 

Posted by Christopher Olah, Research Scientist, Google Brain Team and Alex Mordvintsev, Research Scientist, Google Research Have you ever wondered what goes on inside neural networks? Feature visualization is a powerful tool for digging into neural networks and seeing how they work. Our new articl…


 Richard Szeliski wins 2017 IEEE PAMI Distinguished Researcher award

Facebook Research Scientist Dr. Richard Szeliski was honored today at the International Conference on Computer Vision (ICCV) with the 2017 IEEE […] Richard Szeliski wins 2017 IEEE PAMI Distinguished Researcher award by Kelly Berschauer


 Facebook at ICCV 2017

Computer vision experts from around the world will gather in Venice this week at the International Conference on Computer Vision […] Facebook at ICCV 2017 by Kelly Berschauer


 Classification Driven Dynamic Image Enhancement

 

Convolutional neural networks rely on image texture and structure to serve as discriminative features to classify the image content. Image enhancement techniques can be used as preprocessing steps to help improve the overall image quality and in turn improve the overall effectiveness of a CNN. Exis…


 HDR image reconstruction from a single exposure using deep CNNs

  

Camera sensors can only capture a limited range of luminance simultaneously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting information that have been lost in saturated image areas, in or…


 Learning Wasserstein Embeddings

The Wasserstein distance received a lot of attention recently in the community of machine learning, especially for its principled way of comparing distributions. It has found numerous applications in several hard problems, such as domain adaptation, dimensionality reduction or generative models. Ho…


 Recent Advances in Convolutional Neural Networks

    

In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Leveraging…


 Photo-Guided Exploration of Volume Data Features

 

In this work, we pose the question of whether, by considering qualitative information such as a sample target image as input, one can produce a rendered image of scientific data that is similar to the target. The algorithm resulting from our research allows one to ask the question of whether featur…


 Learning Social Image Embedding with Deep Multimodal Attention Networks

 

Learning social media data embedding by deep models has attracted extensive research interest as well as boomed a lot of applications, such as link prediction, classification, and cross-modal search. However, for social images which contain both link information and multimodal contents (e.g., text …


 Infinite-Label Learning with Semantic Output Codes

We develop a new statistical machine learning paradigm, named infinite-label learning, to annotate a data point with more than one relevant labels from a candidate set, which pools both the finite labels observed at training and a potentially infinite number of previously unseen labels. The infinit…


 Multi-task Domain Adaptation for Deep Learning of Instance Grasping from Simulation

 

Learning-based approaches to robotic manipulation are limited by the scalability of data collection and accessibility of labels. In this paper, we present a multi-task domain adaptation framework for instance grasping in cluttered scenes by utilizing simulated robot experiments. Our neural network …


 Fishing for Clickbaits in Social Images and Texts with Linguistically-Infused Neural Network Models

   

This paper presents the results and conclusions of our participation in the Clickbait Challenge 2017 on automatic clickbait detection in social media. We first describe linguistically-infused neural network models and identify informative representations to predict the level of clickbaiting present…


 A Convex Similarity Index for Sparse Recovery of Missing Image Samples

This paper investigates the problem of recovering missing samples using methods based on sparse representation adapted especially for image signals. Instead of $l_2$-norm or Mean Square Error (MSE), a new perceptual quality measure is used as the similarity criterion between the original and the re…


 Low-shot learning with large-scale diffusion

 

This paper considers the problem of inferring image labels for which only a few labelled examples are available at training time. This setup is often referred to as low-shot learning in the literature, where a standard approach is to re-train the last few layers of a convolutional neural network le…


 Learning to Transfer Initializations for Bayesian Hyperparameter Optimization

   

Hyperparameter optimization undergoes extensive evaluations of validation errors in order to find the best configuration of hyperparameters. Bayesian optimization is now popular for hyperparameter optimization, since it reduces the number of validation error evaluations required. Suppose that we ar…


 Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks

An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task le…