Convolutional neural networks
|
|
- Hubert Cummings
- 5 years ago
- Views:
Transcription
1 Convolutional neural networks
2 Themes Curriculum: Ch 9.1, 9.2 and The simple motivation and idea How it s done Receptive field Pooling Dilated convolutions
3 Resources Learning goals Chapter 9 (not great ) cs231n video: g Video relevant for motivation part : V98 Why is convolutional network good for images and audio? How does a normal convolutional network work? Why is the receptive field important? How can we increase the receptive field? What are pooling, why is it used and what are possible downsides?
4 The simple motivation and idea
5 The simple idea Image filters can enhance image attributes Convolutional neural networks are similar to conventional image filtering Filter kernels are learnt
6 How does a fully connected see the world? A neural network or standard machine learning have to learn that pixels close to each other are more related. A cat moved from one part of a picture to the other is viewed as completely different objects.
7 A shifted frog is seen as completely different
8 A shifted frog is seen as completely different
9 Most image applications are absolute position invariant
10 Building absolute position invariance We can make a sliding classifier: Reusing the same classifier many times for each picture Problems? SVM
11 Building absolute position invariance We can make a sliding classifier: Reusing the same classifier many times for each picture Problems: Restricted field of view Still problems with different sizes
12 Make every layer in a neural network slide
13 Make every layer in a neural network slide Not only the cat classifier is reused, but also partial representations Edge, fur, eye, grass detectors More tolerant to changes in shape and size? Large receptive field? Reuse from sliding is combined with reuse with depth
14 Make every layer in a neural network slide Reuse from sliding is combined with reuse with depth With depth a detector can be reused for different classes etc. With sliding a detector can also be reused for every position A product relationship instead of sum (have not seen any studies)
15 How it s done
16 Convolutional neural network You should all know convolution Difference between convolution and correlation is irrelevant (flipping filter) When we deal with channels or features there are some options
17 Filters and channels (Standard method) An input image have a third dimension (say RGB) A filter/kernel always has the same third dimension
18 Filters and channels Overlapping area is multiplied then summed (dot product) With sliding you get 28x28x1 output
19 Usually we use multiple filters per layer A new kernel/filter slides over the same image Create a new filtered image
20 Many activation maps create a new image If we filter the image 6 times, we get a new image with 6 channels.
21 A onelayer, twofilter network
22 A onelayer, twofilter network
23 A onelayer, twofilter network
24 A onelayer, twofilter network
25 In convolutional networks, layers are 3D...
26 kernels are 4D If we combine all the filters we get a 4D tensor The operation can be viewed as: a matrix multiplication for each spatial position a sum over spatial dimensions This is a useful representation as many deep learning frameworks present it in this way
27 Convolutional neural network consist of multiple layers
28 Convolutional neural network consist of multiple layers
29 Some stack many layers
30 Can a convolutional network remember positions? A fully connected network treat each position different...
31 Can a convolutional network remember positions? A fully connected network treat each position different A convolutional network can first of all keep spatial information in the spatial dimension of the filter bank. More on this later
32 Receptive field How much can the algorithm see
33 How large area influence the end result? With a sliding classifier you get the input size as a receptive field Why do we even want a large receptive field? SVM
34 How large area influence the end result? With a convolutional network the receptive field increase with each layer
35 How large area influence the end result? With a convolutional network the receptive field increase with each layer 3 inputs influence each node in the first hidden layer
36 How large area influence the end result? With a convolutional network the receptive field increase with each layer 3 inputs influence each node in the first hidden layer 5 influence the next...
37 How large area influence the end result? With a convolutional network the receptive field increase with each layer 3 inputs influence each node in the first hidden layer 5 influence the next...
38 How many inputs can influence each output?
39 The receptive field grow with k1 for each layer
40 The receptive field grow with k1 for each layer two 3x3 layers = one 5x5 layers
41 The receptive field grow with k1 for each layer two 3x3 layers = one 5x5 layers So should we use 3x3 or 5x5?
42 The receptive field grow with k1 for each layer two 3x3 layers = one 5x5 layers So should we use 3x3 or 5x5? A 5x5 kernel have: 5*5*(filters_in*filters_out) parameters Two 3x3 kernel have: 2*3*3*(filters_in*filters_out) parameters
43 Smaller spatial filter size is more parameter efficient A network with many parameters generally more training data and computation time A larger receptive field per parameter is good More layers can give more reuse
44 How large receptive field did the 152layer ResNet have (it used 3x3 convolutions)?
45 How large receptive field did the 152layer ResNet have (it used 3x3 convolutions)? 305
46 Increasing the receptive field more efficiently Why do we need to?
47 Increasing the receptive field more efficiently Why do we need to? We only need a certain level of abstraction (still a research topic, but indicated in: Wide Residual Networks Wider or Deeper: Revisiting the ResNet Model for Visual Recognition Residual Networks are Exponential Ensembles of Relatively Shallow Networks Low level features also need spatial context Large networks are expensive in computation time and memory
48 Strided convolutions By skipping positions we can cover a larger area with less computation The effect of the receptive field for the next layer is important
49 The effect of strided convolutions
50 The effect of strided convolutions We still cover the whole input Do we have a larger receptive field? The next layer have a larger receptive field 7 compared to 5
51 The effect of strided convolutions We still cover the whole input Do we have a larger receptive field? The next layer have a larger receptive field 7 compared to 5 The effect can be seen from:
52 The effect of strided convolutions Essentially all the following layers will have a receptive field multiplied by S Green: stride = 2, Red: stride=2 for first, Blue: stride=1
53 With strides, spatial dimensions will become smaller Usually some of the of the network capacity is preserved through an increasing number of channels
54 Can the network still remember positions?
55 Can the network still remember positions? Yes, the network can still encode positional information in the depth dimension A network can pass positional information (right, left etc.) to different channels
56 Pooling Spatial reduction and forcing invariance
57 Maxpooling A strided maximum filtering Choosing the maximum value inside the kernel range
58 Maxpooling: invariance builtin We saw that a network could learn max or average functions to create invariance With maxpooling you explicitly remove some spatial information This can help both position and rotation invariance As we know many image analysis applications seek results invariant to position
59 Maxpooling have some important problems Even if we want our final results to be positionally, we may need positional information in the earlier representations Only a small part of the network is updated with gradients each step (learning slower) We calculate a lot of values that is not used
60 Can the network still remember positions?
61 Can the network still remember positions? Yes, in a similar way as with strides Give a high value to one channel if the target is to the right and a high value to another channel if the target is to the left. The book calls it approximately invariant to small translations Variant features will be harder to learn compared to invariant features
62 Dilated convolutions Larger receptive field, without reducing spatial dimensions or increasing the number of parameters
63 Dilated convolutions Skipping values in the kernel Same as filling the kernel with every other value as zero Still cover all inputs Larger kernel with no extra parameters
64 A growing dilation factor can give similar effect as stride With a constant dilation factor you get the same effect as using a larger kernel With growing dilation you can get an even larger receptive field, while still covering all inputs
65 A growing dilation factor can give similar effect as stride With audio signals, as with this application receptive field is even more important.
66 Next week: Monday: Introduction to tensorflow (small lecture and coding): Why use tensorflow? Tensorflow compared to numpy Friday: Residual networks Convolutional neural networks for segmentation and localisation
Coursework 2. MLP Lecture 7 Convolutional Networks 1
Coursework 2 MLP Lecture 7 Convolutional Networks 1 Coursework 2 - Overview and Objectives Overview: Use a selection of the techniques covered in the course so far to train accurate multi-layer networks
More informationAn Introduction to Convolutional Neural Networks. Alessandro Giusti Dalle Molle Institute for Artificial Intelligence Lugano, Switzerland
An Introduction to Convolutional Neural Networks Alessandro Giusti Dalle Molle Institute for Artificial Intelligence Lugano, Switzerland Sources & Resources - Andrej Karpathy, CS231n http://cs231n.github.io/convolutional-networks/
More informationCSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning Fall 2018/19 6. Convolutional Neural Networks (Some figures adapted from NNDL book) 1 Convolution Neural Networks 1. Convolutional Neural Networks Convolution,
More informationLecture 17 Convolutional Neural Networks
Lecture 17 Convolutional Neural Networks 30 March 2016 Taylor B. Arnold Yale Statistics STAT 365/665 1/22 Notes: Problem set 6 is online and due next Friday, April 8th Problem sets 7,8, and 9 will be due
More informationCSC321 Lecture 11: Convolutional Networks
CSC321 Lecture 11: Convolutional Networks Roger Grosse Roger Grosse CSC321 Lecture 11: Convolutional Networks 1 / 35 Overview What makes vision hard? Vison needs to be robust to a lot of transformations
More informationConvolutional Networks Overview
Convolutional Networks Overview Sargur Srihari 1 Topics Limitations of Conventional Neural Networks The convolution operation Convolutional Networks Pooling Convolutional Network Architecture Advantages
More informationDetection and Segmentation. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 11 -
Lecture 11: Detection and Segmentation Lecture 11-1 May 10, 2017 Administrative Midterms being graded Please don t discuss midterms until next week - some students not yet taken A2 being graded Project
More informationDeep Learning. Dr. Johan Hagelbäck.
Deep Learning Dr. Johan Hagelbäck johan.hagelback@lnu.se http://aiguy.org Image Classification Image classification can be a difficult task Some of the challenges we have to face are: Viewpoint variation:
More informationGenerating an appropriate sound for a video using WaveNet.
Australian National University College of Engineering and Computer Science Master of Computing Generating an appropriate sound for a video using WaveNet. COMP 8715 Individual Computing Project Taku Ueki
More informationCS 7643: Deep Learning
CS 7643: Deep Learning Topics: Toeplitz matrices and convolutions = matrix-mult Dilated/a-trous convolutions Backprop in conv layers Transposed convolutions Dhruv Batra Georgia Tech HW1 extension 09/22
More informationLecture 23 Deep Learning: Segmentation
Lecture 23 Deep Learning: Segmentation COS 429: Computer Vision Thanks: most of these slides shamelessly adapted from Stanford CS231n: Convolutional Neural Networks for Visual Recognition Fei-Fei Li, Andrej
More informationIntroduction to Machine Learning
Introduction to Machine Learning Deep Learning Barnabás Póczos Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio Geoffrey Hinton Yann LeCun 2
More informationDigital Image Processing. Digital Image Fundamentals II 12 th June, 2017
Digital Image Processing Digital Image Fundamentals II 12 th June, 2017 Image Enhancement Image Enhancement Types of Image Enhancement Operations Neighborhood Operations on Images Spatial Filtering Filtering
More informationCPSC 340: Machine Learning and Data Mining. Convolutional Neural Networks Fall 2018
CPSC 340: Machine Learning and Data Mining Convolutional Neural Networks Fall 2018 Admin Mike and I finish CNNs on Wednesday. After that, we will cover different topics: Mike will do a demo of training
More informationClassification Accuracies of Malaria Infected Cells Using Deep Convolutional Neural Networks Based on Decompressed Images
Classification Accuracies of Malaria Infected Cells Using Deep Convolutional Neural Networks Based on Decompressed Images Yuhang Dong, Zhuocheng Jiang, Hongda Shen, W. David Pan Dept. of Electrical & Computer
More informationBiologically Inspired Computation
Biologically Inspired Computation Deep Learning & Convolutional Neural Networks Joe Marino biologically inspired computation biological intelligence flexible capable of detecting/ executing/reasoning about
More information11/13/18. Introduction to RNNs for NLP. About Me. Overview SHANG GAO
Introduction to RNNs for NLP SHANG GAO About Me PhD student in the Data Science and Engineering program Took Deep Learning last year Work in the Biomedical Sciences, Engineering, and Computing group at
More informationUnderstanding Neural Networks : Part II
TensorFlow Workshop 2018 Understanding Neural Networks Part II : Convolutional Layers and Collaborative Filters Nick Winovich Department of Mathematics Purdue University July 2018 Outline 1 Convolutional
More informationCONVOLUTIONAL NEURAL NETWORKS: MOTIVATION, CONVOLUTION OPERATION, ALEXNET
CONVOLUTIONAL NEURAL NETWORKS: MOTIVATION, CONVOLUTION OPERATION, ALEXNET MOTIVATION Fully connected neural network Example 1000x1000 image 1M hidden units 10 12 (= 10 6 10 6 ) parameters! Observation
More information6. Convolutional Neural Networks
6. Convolutional Neural Networks CS 519 Deep Learning, Winter 2016 Fuxin Li With materials from Zsolt Kira Quiz coming up Next Tuesday (1/26) 15 minutes Topics: Optimization Basic neural networks No Convolutional
More informationResearch on Hand Gesture Recognition Using Convolutional Neural Network
Research on Hand Gesture Recognition Using Convolutional Neural Network Tian Zhaoyang a, Cheng Lee Lung b a Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China E-mail address:
More informationNumber Plate Detection with a Multi-Convolutional Neural Network Approach with Optical Character Recognition for Mobile Devices
J Inf Process Syst, Vol.12, No.1, pp.100~108, March 2016 http://dx.doi.org/10.3745/jips.04.0022 ISSN 1976-913X (Print) ISSN 2092-805X (Electronic) Number Plate Detection with a Multi-Convolutional Neural
More informationSemantic Segmentation on Resource Constrained Devices
Semantic Segmentation on Resource Constrained Devices Sachin Mehta University of Washington, Seattle In collaboration with Mohammad Rastegari, Anat Caspi, Linda Shapiro, and Hannaneh Hajishirzi Project
More informationPractical Image and Video Processing Using MATLAB
Practical Image and Video Processing Using MATLAB Chapter 10 Neighborhood processing What will we learn? What is neighborhood processing and how does it differ from point processing? What is convolution
More informationDeep Learning for Human Activity Recognition: A Resource Efficient Implementation on Low-Power Devices
Deep Learning for Human Activity Recognition: A Resource Efficient Implementation on Low-Power Devices Daniele Ravì, Charence Wong, Benny Lo and Guang-Zhong Yang To appear in the proceedings of the IEEE
More informationDeep Learning Basics Lecture 9: Recurrent Neural Networks. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 9: Recurrent Neural Networks Princeton University COS 495 Instructor: Yingyu Liang Introduction Recurrent neural networks Dates back to (Rumelhart et al., 1986) A family of
More informationConvolutional Neural Networks
Convolutional Neural Networks Convolution, LeNet, AlexNet, VGGNet, GoogleNet, Resnet, DenseNet, CAM, Deconvolution Sept 17, 2018 Aaditya Prakash Convolution Convolution Demo Convolution Convolution in
More informationLecture 11-1 CNN introduction. Sung Kim
Lecture 11-1 CNN introduction Sung Kim 'The only limit is your imagination' http://itchyi.squarespace.com/thelatest/2012/5/17/the-only-limit-is-your-imagination.html Lecture 7: Convolutional
More informationCS 4501: Introduction to Computer Vision. Filtering and Edge Detection
CS 451: Introduction to Computer Vision Filtering and Edge Detection Connelly Barnes Slides from Jason Lawrence, Fei Fei Li, Juan Carlos Niebles, Misha Kazhdan, Allison Klein, Tom Funkhouser, Adam Finkelstein,
More informationSynthetic View Generation for Absolute Pose Regression and Image Synthesis: Supplementary material
Synthetic View Generation for Absolute Pose Regression and Image Synthesis: Supplementary material Pulak Purkait 1 pulak.cv@gmail.com Cheng Zhao 2 irobotcheng@gmail.com Christopher Zach 1 christopher.m.zach@gmail.com
More information>>> from numpy import random as r >>> I = r.rand(256,256);
WHAT IS AN IMAGE? >>> from numpy import random as r >>> I = r.rand(256,256); Think-Pair-Share: - What is this? What does it look like? - Which values does it take? - How many values can it take? - Is it
More informationDeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. ECE 289G: Paper Presentation #3 Philipp Gysel
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition ECE 289G: Paper Presentation #3 Philipp Gysel Autonomous Car ECE 289G Paper Presentation, Philipp Gysel Slide 2 Source: maps.google.com
More informationMatlab (see Homework 1: Intro to Matlab) Linear Filters (Reading: 7.1, ) Correlation. Convolution. Linear Filtering (warm-up slide) R ij
Matlab (see Homework : Intro to Matlab) Starting Matlab from Unix: matlab & OR matlab nodisplay Image representations in Matlab: Unsigned 8bit values (when first read) Values in range [, 255], = black,
More informationVision Review: Image Processing. Course web page:
Vision Review: Image Processing Course web page: www.cis.udel.edu/~cer/arv September 7, Announcements Homework and paper presentation guidelines are up on web page Readings for next Tuesday: Chapters 6,.,
More information>>> from numpy import random as r >>> I = r.rand(256,256);
WHAT IS AN IMAGE? >>> from numpy import random as r >>> I = r.rand(256,256); Think-Pair-Share: - What is this? What does it look like? - Which values does it take? - How many values can it take? - Is it
More informationDeep Neural Network Architectures for Modulation Classification
Deep Neural Network Architectures for Modulation Classification Xiaoyu Liu, Diyu Yang, and Aly El Gamal School of Electrical and Computer Engineering Purdue University Email: {liu1962, yang1467, elgamala}@purdue.edu
More informationLecture 13 Register Allocation: Coalescing
Lecture 13 Register llocation: Coalescing I. Motivation II. Coalescing Overview III. lgorithms: Simple & Safe lgorithm riggs lgorithm George s lgorithm Phillip. Gibbons 15-745: Register Coalescing 1 Review:
More informationMore image filtering , , Computational Photography Fall 2017, Lecture 4
More image filtering http://graphics.cs.cmu.edu/courses/15-463 15-463, 15-663, 15-862 Computational Photography Fall 2017, Lecture 4 Course announcements Any questions about Homework 1? - How many of you
More informationNeural Network Part 4: Recurrent Neural Networks
Neural Network Part 4: Recurrent Neural Networks Yingyu Liang Computer Sciences 760 Fall 2017 http://pages.cs.wisc.edu/~yliang/cs760/ Some of the slides in these lectures have been adapted/borrowed from
More informationThe Art of Neural Nets
The Art of Neural Nets Marco Tavora marcotav65@gmail.com Preamble The challenge of recognizing artists given their paintings has been, for a long time, far beyond the capability of algorithms. Recent advances
More informationStudy guide for Graduate Computer Vision
Study guide for Graduate Computer Vision Erik G. Learned-Miller Department of Computer Science University of Massachusetts, Amherst Amherst, MA 01003 November 23, 2011 Abstract 1 1. Know Bayes rule. What
More informationRobert Collins CSE486, Penn State. Lecture 3: Linear Operators
Lecture : Linear Operators Administrivia I have put some Matlab image tutorials on Angel. Please take a look if you are unfamiliar with Matlab or the image toolbox. I have posted Homework on Angel. It
More informationTemplates and Image Pyramids
Templates and Image Pyramids 09/06/11 Computational Photography Derek Hoiem, University of Illinois Project 1 Due Monday at 11:59pm Options for displaying results Web interface or redirect (http://www.pa.msu.edu/services/computing/faq/autoredirect.html)
More informationA Fuller Understanding of Fully Convolutional Networks. Evan Shelhamer* Jonathan Long* Trevor Darrell UC Berkeley in CVPR'15, PAMI'16
A Fuller Understanding of Fully Convolutional Networks Evan Shelhamer* Jonathan Long* Trevor Darrell UC Berkeley in CVPR'15, PAMI'16 1 pixels in, pixels out colorization Zhang et al.2016 monocular depth
More informationTiny ImageNet Challenge Investigating the Scaling of Inception Layers for Reduced Scale Classification Problems
Tiny ImageNet Challenge Investigating the Scaling of Inception Layers for Reduced Scale Classification Problems Emeric Stéphane Boigné eboigne@stanford.edu Jan Felix Heyse heyse@stanford.edu Abstract Scaling
More informationA Spatial Mean and Median Filter For Noise Removal in Digital Images
A Spatial Mean and Median Filter For Noise Removal in Digital Images N.Rajesh Kumar 1, J.Uday Kumar 2 Associate Professor, Dept. of ECE, Jaya Prakash Narayan College of Engineering, Mahabubnagar, Telangana,
More informationFiltering in the spatial domain (Spatial Filtering)
Filtering in the spatial domain (Spatial Filtering) refers to image operators that change the gray value at any pixel (x,y) depending on the pixel values in a square neighborhood centered at (x,y) using
More information02/02/10. Image Filtering. Computer Vision CS 543 / ECE 549 University of Illinois. Derek Hoiem
2/2/ Image Filtering Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem Questions about HW? Questions about class? Room change starting thursday: Everitt 63, same time Key ideas from last
More informationA Neural Algorithm of Artistic Style (2015)
A Neural Algorithm of Artistic Style (2015) Leon A. Gatys, Alexander S. Ecker, Matthias Bethge Nancy Iskander (niskander@dgp.toronto.edu) Overview of Method Content: Global structure. Style: Colours; local
More information신경망기반자동번역기술. Konkuk University Computational Intelligence Lab. 김강일
신경망기반자동번역기술 Konkuk University Computational Intelligence Lab. http://ci.konkuk.ac.kr kikim01@kunkuk.ac.kr 김강일 Index Issues in AI and Deep Learning Overview of Machine Translation Advanced Techniques in
More informationAutomatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model
Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model Yuzhou Hu Departmentof Electronic Engineering, Fudan University,
More informationDigital Media. Lecture 4: Bitmapped images: Compression & Convolution Georgia Gwinnett College School of Science and Technology Dr.
Digital Media Lecture 4: Bitmapped images: Compression & Convolution Georgia Gwinnett College School of Science and Technology Dr. Mark Iken Bitmapped image compression Consider this image: With no compression...
More informationFiltering. Image Enhancement Spatial and Frequency Based
Filtering Image Enhancement Spatial and Frequency Based Brent M. Dingle, Ph.D. 2015 Game Design and Development Program Mathematics, Statistics and Computer Science University of Wisconsin - Stout Lecture
More informationImage features: Histograms, Aliasing, Filters, Orientation and HOG. D.A. Forsyth
Image features: Histograms, Aliasing, Filters, Orientation and HOG D.A. Forsyth Simple color features Histogram of image colors in a window Opponent color representations R-G B-Y=B-(R+G)/2 Intensity=(R+G+B)/3
More informationConvolutional Neural Network-based Steganalysis on Spatial Domain
Convolutional Neural Network-based Steganalysis on Spatial Domain Dong-Hyun Kim, and Hae-Yeoun Lee Abstract Steganalysis has been studied to detect the existence of hidden messages by steganography. However,
More informationRecurrent neural networks Modelling sequential data. MLP Lecture 9 Recurrent Neural Networks 1: Modelling sequential data 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 Recurrent Neural Networks 1: Modelling sequential data 1 Recurrent Neural Networks 1: Modelling sequential data Steve Renals Machine Learning
More informationIMAGE PROCESSING PROJECT REPORT NUCLEUS CLASIFICATION
ABSTRACT : The Main agenda of this project is to segment and analyze the a stack of image, where it contains nucleus, nucleolus and heterochromatin. Find the volume, Density, Area and circularity of the
More informationConvolutional Networks for Image Segmentation: U-Net 1, DeconvNet 2, and SegNet 3
Convolutional Networks for Image Segmentation: U-Net 1, DeconvNet 2, and SegNet 3 1 Olaf Ronneberger, Philipp Fischer, Thomas Brox (Freiburg, Germany) 2 Hyeonwoo Noh, Seunghoon Hong, Bohyung Han (POSTECH,
More informationTo Infinity And Beyond. Computer Vision for Astronomy
To Infinity And Beyond Computer Vision for Astronomy Ryan Fox ryan@foxrow.com @ryan_fox foxrow.com 1. Image Processing 2. Computer Vision 3. To Infinity and Beyond How computers see How computers see 006
More informationHardware-based Image Retrieval and Classifier System
Hardware-based Image Retrieval and Classifier System Jason Isaacs, Joe Petrone, Geoffrey Wall, Faizal Iqbal, Xiuwen Liu, and Simon Foo Department of Electrical and Computer Engineering Florida A&M - Florida
More informationComparison of Google Image Search and ResNet Image Classification Using Image Similarity Metrics
University of Arkansas, Fayetteville ScholarWorks@UARK Computer Science and Computer Engineering Undergraduate Honors Theses Computer Science and Computer Engineering 5-2018 Comparison of Google Image
More informationTHE problem of automating the solving of
CS231A FINAL PROJECT, JUNE 2016 1 Solving Large Jigsaw Puzzles L. Dery and C. Fufa Abstract This project attempts to reproduce the genetic algorithm in a paper entitled A Genetic Algorithm-Based Solver
More informationarxiv: v1 [stat.ml] 10 Nov 2017
Poverty Prediction with Public Landsat 7 Satellite Imagery and Machine Learning arxiv:1711.03654v1 [stat.ml] 10 Nov 2017 Anthony Perez Department of Computer Science Stanford, CA 94305 aperez8@stanford.edu
More informationDEEP LEARNING ON RF DATA. Adam Thompson Senior Solutions Architect March 29, 2018
DEEP LEARNING ON RF DATA Adam Thompson Senior Solutions Architect March 29, 2018 Background Information Signal Processing and Deep Learning Radio Frequency Data Nuances AGENDA Complex Domain Representations
More informationImage processing for gesture recognition: from theory to practice. Michela Goffredo University Roma TRE
Image processing for gesture recognition: from theory to practice 2 Michela Goffredo University Roma TRE goffredo@uniroma3.it Image processing At this point we have all of the basics at our disposal. We
More informationImage Manipulation Detection using Convolutional Neural Network
Image Manipulation Detection using Convolutional Neural Network Dong-Hyun Kim 1 and Hae-Yeoun Lee 2,* 1 Graduate Student, 2 PhD, Professor 1,2 Department of Computer Software Engineering, Kumoh National
More informationImage Filtering Josef Pelikán & Alexander Wilkie CGG MFF UK Praha
Image Filtering 1995-216 Josef Pelikán & Alexander Wilkie CGG MFF UK Praha pepca@cgg.mff.cuni.cz http://cgg.mff.cuni.cz/~pepca/ 1 / 32 Image Histograms Frequency table of individual brightness (and sometimes
More informationGPU ACCELERATED DEEP LEARNING WITH CUDNN
GPU ACCELERATED DEEP LEARNING WITH CUDNN Larry Brown Ph.D. March 2015 AGENDA 1 Introducing cudnn and GPUs 2 Deep Learning Context 3 cudnn V2 4 Using cudnn 2 Introducing cudnn and GPUs 3 HOW GPU ACCELERATION
More informationSpatial Transformer Networks
Spatial Transformer Networks Kaichun Mo Shanghai Jiao Tong University daerduomkch@sjtueducn July 28, 2015 Kaichun Mo (SJTU@Cornell) STN July 28, 2015 1 / 29 Overview 1 Spatial Transformer Network 2 Caffe:
More informationAutomated Image Timestamp Inference Using Convolutional Neural Networks
Automated Image Timestamp Inference Using Convolutional Neural Networks Prafull Sharma prafull7@stanford.edu Michel Schoemaker michel92@stanford.edu Stanford University David Pan napdivad@stanford.edu
More informationTemplates and Image Pyramids
Templates and Image Pyramids 09/07/17 Computational Photography Derek Hoiem, University of Illinois Why does a lower resolution image still make sense to us? What do we lose? Image: http://www.flickr.com/photos/igorms/136916757/
More information10mW CMOS Retina and Classifier for Handheld, 1000Images/s Optical Character Recognition System
TP 12.1 10mW CMOS Retina and Classifier for Handheld, 1000Images/s Optical Character Recognition System Peter Masa, Pascal Heim, Edo Franzi, Xavier Arreguit, Friedrich Heitger, Pierre Francois Ruedi, Pascal
More informationRecurrent neural networks Modelling sequential data. MLP Lecture 9 Recurrent Networks 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 Recurrent Networks 1 Recurrent Networks Steve Renals Machine Learning Practical MLP Lecture 9 16 November 2016 MLP Lecture 9 Recurrent
More informationarxiv: v3 [cs.cv] 18 Dec 2018
Video Colorization using CNNs and Keyframes extraction: An application in saving bandwidth Ankur Singh 1 Anurag Chanani 2 Harish Karnick 3 arxiv:1812.03858v3 [cs.cv] 18 Dec 2018 Abstract In this paper,
More informationFFT analysis in practice
FFT analysis in practice Perception & Multimedia Computing Lecture 13 Rebecca Fiebrink Lecturer, Department of Computing Goldsmiths, University of London 1 Last Week Review of complex numbers: rectangular
More informationLesson 08. Convolutional Neural Network. Ing. Marek Hrúz, Ph.D. Katedra Kybernetiky Fakulta aplikovaných věd Západočeská univerzita v Plzni.
Lesson 08 Convolutional Neural Network Ing. Marek Hrúz, Ph.D. Katedra Kybernetiky Fakulta aplikovaných věd Západočeská univerzita v Plzni Lesson 08 Convolution we will consider 2D convolution the result
More informationFilters. Materials from Prof. Klaus Mueller
Filters Materials from Prof. Klaus Mueller Think More about Pixels What exactly a pixel is in an image or on the screen? Solid square? This cannot be implemented A dot? Yes, but size matters Pixel Dots
More informationIntroduction to Machine Learning
Introduction to Machine Learning Perceptron Barnabás Póczos Contents History of Artificial Neural Networks Definitions: Perceptron, Multi-Layer Perceptron Perceptron algorithm 2 Short History of Artificial
More informationLecture 19: Depth Cameras. Kayvon Fatahalian CMU : Graphics and Imaging Architectures (Fall 2011)
Lecture 19: Depth Cameras Kayvon Fatahalian CMU 15-869: Graphics and Imaging Architectures (Fall 2011) Continuing theme: computational photography Cheap cameras capture light, extensive processing produces
More informationDeep learning architectures for music audio classification: a personal (re)view
Deep learning architectures for music audio classification: a personal (re)view Jordi Pons jordipons.me @jordiponsdotme Music Technology Group Universitat Pompeu Fabra, Barcelona Acronyms MLP: multi layer
More informationROAD RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS
Bulletin of the Transilvania University of Braşov Vol. 10 (59) No. 2-2017 Series I: Engineering Sciences ROAD RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS E. HORVÁTH 1 C. POZNA 2 Á. BALLAGI 3
More informationEn ny æra for uthenting av informasjon fra satellittbilder ved hjelp av maskinlæring
En ny æra for uthenting av informasjon fra satellittbilder ved hjelp av maskinlæring Mathilde Ørstavik og Terje Midtbø Mathilde Ørstavik and Terje Midtbø, A New Era for Feature Extraction in Remotely Sensed
More informationPACS photometry on extended sources
PACS photometry on extended sources Total flux experiments Bruno Altieri on behalf of Marc Sauvage 1. Point-source photometry status 2. Prospect on extended emission photometry from theory 3. Results from
More informationNumerical Derivatives See also T&V, Appendix A.2 Gradient = vector of partial derivatives of image I(x,y) = [di(x,y)/dx, di(x,y)/dy]
I have put some Matlab image tutorials on Angel. Please take a look i you are unamiliar with Matlab or the image toolbox. Lecture : Linear Operators Administrivia I have posted Homework on Angel. It is
More informationClassification of Road Images for Lane Detection
Classification of Road Images for Lane Detection Mingyu Kim minkyu89@stanford.edu Insun Jang insunj@stanford.edu Eunmo Yang eyang89@stanford.edu 1. Introduction In the research on autonomous car, it is
More informationMotion illusion, rotating snakes
Motion illusion, rotating snakes Image Filtering 9/4/2 Computer Vision James Hays, Brown Graphic: unsharp mask Many slides by Derek Hoiem Next three classes: three views of filtering Image filters in spatial
More informationSolution Q.1 What is a digital Image? Difference between Image Processing
I Mid Term Test Subject: DIP Branch: CS Sem: VIII th Sem MM:10 Faculty Name: S.N.Tazi All Question Carry Equal Marks Q.1 What is a digital Image? Difference between Image Processing and Computer Graphics?
More informationA Primer on Human Vision: Insights and Inspiration for Computer Vision
A Primer on Human Vision: Insights and Inspiration for Computer Vision Guest Lecture: Marius Cătălin Iordan CS 131 - Computer Vision: Foundations and Applications 27 October 2014 detection recognition
More informationSIMULATION-BASED MODEL CONTROL USING STATIC HAND GESTURES IN MATLAB
SIMULATION-BASED MODEL CONTROL USING STATIC HAND GESTURES IN MATLAB S. Kajan, J. Goga Institute of Robotics and Cybernetics, Faculty of Electrical Engineering and Information Technology, Slovak University
More informationHigh Level Computer Vision SS2015
High Level Computer Vision SS2015 Exercise 2: Object Identification (Released on 8th May, due on 15th May. Send your solution to walon@mpi-inf.mpg.de with adding [hlcv] to the caption) Question 1: Image
More informationCounterfeit Bill Detection Algorithm using Deep Learning
Counterfeit Bill Detection Algorithm using Deep Learning Soo-Hyeon Lee 1 and Hae-Yeoun Lee 2,* 1 Undergraduate Student, 2 Professor 1,2 Department of Computer Software Engineering, Kumoh National Institute
More informationImage Enhancement using Histogram Equalization and Spatial Filtering
Image Enhancement using Histogram Equalization and Spatial Filtering Fari Muhammad Abubakar 1 1 Department of Electronics Engineering Tianjin University of Technology and Education (TUTE) Tianjin, P.R.
More informationContinued. Introduction to Computer Vision CSE 252a Lecture 11
Continued Introduction to Computer Vision CSE 252a Lecture 11 The appearance of colors Color appearance is strongly affected by (at least): Spectrum of lighting striking the retina other nearby colors
More informationSmall World Network Architectures. NIPS 2017 Workshop
Small World Network Architectures NIPS 2017 Workshop Small World Networks We'd like to explore training models with very wide hidden states. More active memory, more information bandwidth, more easily
More informationComputer Graphics (Fall 2011) Outline. CS 184 Guest Lecture: Sampling and Reconstruction Ravi Ramamoorthi
Computer Graphics (Fall 2011) CS 184 Guest Lecture: Sampling and Reconstruction Ravi Ramamoorthi Some slides courtesy Thomas Funkhouser and Pat Hanrahan Adapted version of CS 283 lecture http://inst.eecs.berkeley.edu/~cs283/fa10
More informationComputing for Engineers in Python
Computing for Engineers in Python Lecture 10: Signal (Image) Processing Autumn 2011-12 Some slides incorporated from Benny Chor s course 1 Lecture 9: Highlights Sorting, searching and time complexity Preprocessing
More informationRadio Deep Learning Efforts Showcase Presentation
Radio Deep Learning Efforts Showcase Presentation November 2016 hume@vt.edu www.hume.vt.edu Tim O Shea Senior Research Associate Program Overview Program Objective: Rethink fundamental approaches to how
More informationNeural Networks The New Moore s Law
Neural Networks The New Moore s Law Chris Rowen, PhD, FIEEE CEO Cognite Ventures December 216 Outline Moore s Law Revisited: Efficiency Drives Productivity Embedded Neural Network Product Segments Efficiency
More informationApplication of Deep Learning in Software Security Detection
2018 International Conference on Computational Science and Engineering (ICCSE 2018) Application of Deep Learning in Software Security Detection Lin Li1, 2, Ying Ding1, 2 and Jiacheng Mao1, 2 College of
More informationDesign of Practical Color Filter Array Interpolation Algorithms for Cameras, Part 2
Design of Practical Color Filter Array Interpolation Algorithms for Cameras, Part 2 James E. Adams, Jr. Eastman Kodak Company jeadams @ kodak. com Abstract Single-chip digital cameras use a color filter
More information