Convolu'onal Neural Networks. November 17, 2015
|
|
|
- Stanley Taylor
- 5 years ago
- Views:
Transcription
1 Convolu'onal Neural Networks November 17, 2015
2 Ar'ficial Neural Networks Feedforward neural networks
3 Ar'ficial Neural Networks Feedforward, fully-connected neural networks
4 Ar'ficial Neural Networks Feedforward, fully-connected neural networks Large modeling capacity
5 Ar'ficial Neural Networks Feedforward, fully-connected neural networks Large modeling capacity Require large amounts of data
6 Ar'ficial Neural Networks Feedforward, fully-connected neural networks Large modeling capacity Require large amounts of data Work fairly well for handwrihen digits
7
8 Natural images? not so much.
9
10 Natural Images
11 Much more detail Natural Images
12 Natural Images Much more detail Intricate spa'al rela'onships
13 Natural Images Much more detail Intricate spa'al rela'onships More variety within a class of examples
14 Natural Images Much more detail Intricate spa'al rela'onships More variety within a class of examples
15 Natural Images Much more detail Intricate spa'al rela'onships More variety within a class of examples Natural varia'ons Color Viewing angle Ligh'ng Size Posi'on
16 Can we build a beher network?
17 Take inspira'on from neuroscience
18 Biological Vision
19 Biological Vision
20 Biological Vision Hubel & Wiesel (1950s)
21 Biological Vision Hubel & Wiesel (1950s)
22 Biological Vision Hubel & Wiesel (1950s) Record from neurons in V1
23 Biological Vision Hubel & Wiesel (1950s) Record from neurons in V1 Present moving gra'ngs
24 Biological Vision Hubel & Wiesel (1950s) Record from neurons in V1 Present moving gra'ngs
25 Biological Vision
26 Biological Vision Simple and complex cells
27 Biological Vision Simple and complex cells
28 Higher visual areas Biological Vision
29 Biological Vision Higher visual areas Encode complex s'muli
30 Biological Vision Higher visual areas Encode complex s'muli Professor Doris Tsao, Caltech
31 Biological Vision Friewald, 2009 & 2010
32 Biological Vision
33 Biological Vision Hierarchical representa'on
34 Biological Vision Hierarchical representa'on Map of visual space at lower levels
35 Biological Vision Hierarchical representa'on Map of visual space at lower levels Highly connected at upper levels of the hierarchy
36 How do we turn this into a model?
37 Convolu'on & Pooling
38 Convolu'onal Opera'on
39 Convolu'onal Opera'on
40 Pooling Opera'on
41 LeNet LeCun, 1989
42 AI Winter
43 AI Winter
44 AI Winter Convolu'onal neural networks are great, but
45 AI Winter Convolu'onal neural networks are great, but They are hard to train
46 AI Winter Convolu'onal neural networks are great, but They are hard to train They take a long 'me to train
47 AI Winter Convolu'onal neural networks are great, but They are hard to train They take a long 'me to train We don t have enough data to train them
48 GPUs
49 GPU Graphics Processing Unit
50 GPU Graphics Processing Unit Rendering images is computa'onally intensive
51 GPU Graphics Processing Unit Rendering images is computa'onally intensive Parallel processing architecture to handle this task
52 GPU Graphics Processing Unit Rendering images is computa'onally intensive Parallel processing architecture to handle this task Can also handle matrix mul'plica'on opera'ons
53 GPU Graphics Processing Unit Rendering images is computa'onally intensive Parallel processing architecture to handle this task Can also handle matrix mul'plica'on opera'ons
54 Big Data
55 Cameras Big Data
56 Big Data Cameras Digital cameras, smartphones
57 Big Data Cameras Digital cameras, smartphones Internet
58 Big Data Cameras Digital cameras, smartphones Internet Anyone can upload a picture
59 Big Data Cameras Digital cameras, smartphones Internet Anyone can upload a picture Crowdsourcing
60 Big Data Cameras Digital cameras, smartphones Internet Anyone can upload a picture Crowdsourcing ImageNet
61 ImageNet Large Scale Visual Recogni'on Challenge
62 ImageNet Large Scale Visual Recogni'on Challenge Object recogni'on task
63 ImageNet Large Scale Visual Recogni'on Challenge Object recogni'on task 1.2 million images
64 ImageNet Large Scale Visual Recogni'on Challenge Object recogni'on task 1.2 million images 1,000 classes of objects
65 ILSVRC 2012
66 ILSVRC 2012 Krizhevsky, et al. use a deep convolu'onal network
67 ILSVRC 2012 Krizhevsky, et al. use a deep convolu'onal network Nearly halve the best error rate of the previous year
68 ILSVRC 2012 Krizhevsky, et al. use a deep convolu'onal network Nearly halve the best error rate of the previous year Trained using GPUs and a few other tricks
69 Rec'fied Linear Units (ReLUs)
70 Rec'fied Linear Units (ReLUs) Researchers had primarily been using sigmoid non-lineari'es
71 Rec'fied Linear Units (ReLUs) Researchers had primarily been using sigmoid non-lineari'es Vanishing gradient, satura'on
72 Rec'fied Linear Units (ReLUs) Researchers had primarily been using sigmoid non-lineari'es Vanishing gradient, satura'on Instead, use ReLU
73 Rec'fied Linear Units (ReLUs) Researchers had primarily been using sigmoid non-lineari'es Vanishing gradient, satura'on Instead, use ReLU Works much beher!
74 Dropout
75 Dropout Unreliable connec'ons between layers
76 Dropout Unreliable connec'ons between layers Randomly have connec'ons drop out
77 Dropout Unreliable connec'ons between layers Randomly have connec'ons drop out Acts as a regularizer
78 Dropout Unreliable connec'ons between layers Randomly have connec'ons drop out Acts as a regularizer Forces the network to learn general features
79 AlexNet Image Convolu'on and Max Pooling Layers Fully Connected Layers
80 Features
81 Conv1 Features
82 Top Image Patches Features
83
84
85
86
87
88
89
90
91
92 2014
93 GoogLeNet 2014
94 GoogLeNet 2014
95 GoogLeNet 2014
96 GoogLeNet 2014
97 GoogLeNet 2014
98 GoogLeNet 2014
99 2014 GoogLeNet 7% top-5 error
100 Microsoh 2015
101 2015 Microsoh 5% top-5 accuracy
102 2015 Microsoh 5% top-5 accuracy Surpassed human level performance
103 Issues
104 Adversarial examples Issues
105 Issues Adversarial examples Lacking a theore'cal understanding of these models
106 Issues Adversarial examples Lacking a theore'cal understanding of these models Learning is dependent on class labels. Unsupervised deep learning is less developed.
107 Sohware Packages Caffe - hhps://github.com/bvlc/caffe Torch - hhps://github.com/torch/torch7 Theano - hhps://github.com/theano/theano Neon - hhps://github.com/nervanasystems/neon TensorFlow - hhps://github.com/tensorflow/tensorflow
108 Resources LeNet: Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. HandwriHen digit recogni'on with a back-propaga'on network. Advances in Neural Informa6on Processing Systems ImageNet: Olga Russakovsky*, Jia Deng*, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei. (* = equal contribu'on) ImageNet Large Scale Visual Recogni'on Challenge. arxiv: , AlexNet: Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classifica'on with deep convolu'onal neural networks." Advances in neural informa6on processing systems Network Visualiza7on: Zeiler, MaHhew D., and Rob Fergus. "Visualizing and understanding convolu'onal networks." Computer Vision ECCV Springer Interna'onal Publishing, GoogLeNet: Szegedy, Chris'an, et al. "Going deeper with convolu'ons." arxiv preprint arxiv: (2014). Microso< Network: He, Kaiming, et al. "Delving deep into rec'fiers: Surpassing human-level performance on imagenet classifica'on." arxiv preprint arxiv: (2015). Adversarial Examples: Szegedy, Chris'an, et al. "Intriguing proper'es of neural networks." arxiv preprint arxiv: (2013).
Biologically Inspired Computation
Biologically Inspired Computation Deep Learning & Convolutional Neural Networks Joe Marino biologically inspired computation biological intelligence flexible capable of detecting/ executing/reasoning about
Lecture 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
arxiv: v2 [cs.cv] 11 Oct 2016
![arxiv: v2 [cs.cv] 11 Oct 2016](/thumbs/94/119169670.jpg "arxiv: v2 [cs.cv] 11 Oct 2016")
Xception: Deep Learning with Depthwise Separable Convolutions arxiv:1610.02357v2 [cs.cv] 11 Oct 2016 François Chollet Google, Inc. fchollet@google.com Monday 10 th October, 2016 Abstract We present an
Xception: Deep Learning with Depthwise Separable Convolutions
Xception: Deep Learning with Depthwise Separable Convolutions François Chollet Google, Inc. fchollet@google.com 1 A variant of the process is to independently look at width-wise correarxiv:1610.02357v3
ON CLASSIFICATION OF DISTORTED IMAGES WITH DEEP CONVOLUTIONAL NEURAL NETWORKS. Yiren Zhou, Sibo Song, Ngai-Man Cheung
ON CLASSIFICATION OF DISTORTED IMAGES WITH DEEP CONVOLUTIONAL NEURAL NETWORKS Yiren Zhou, Sibo Song, Ngai-Man Cheung Singapore University of Technology and Design In this section, we briefly introduce
Introduction 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
Convolutional Neural Networks. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 5-1
Lecture 5: Convolutional Neural Networks Lecture 5-1 Administrative Assignment 1 due Thursday April 20, 11:59pm on Canvas Assignment 2 will be released Thursday Lecture 5-2 Last time: Neural Networks Linear
PROJECT REPORT. Using Deep Learning to Classify Malignancy Associated Changes
Using Deep Learning to Classify Malignancy Associated Changes Hakan Wieslander, Gustav Forslid Project in Computational Science: Report January 2017 PROJECT REPORT Department of Information Technology
یادآوری: خالصه CNN. ConvNet
1 ConvNet یادآوری: خالصه CNN شبکه عصبی کانولوشنال یا Convolutional Neural Networks یا نوعی از شبکههای عصبی عمیق مدل یادگیری آن باناظر.اصالح وزنها با الگوریتم back-propagation مناسب برای داده های حجیم و
Convolutional Neural Networks. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 5-1
Lecture 5: Convolutional Neural Networks Lecture 5-1 Administrative Assignment 1 due Wednesday April 17, 11:59pm - Important: tag your solutions with the corresponding hw question in gradescope! - Some
Camera Model Identification With The Use of Deep Convolutional Neural Networks
Camera Model Identification With The Use of Deep Convolutional Neural Networks Amel TUAMA 2,3, Frédéric COMBY 2,3, and Marc CHAUMONT 1,2,3 (1) University of Nîmes, France (2) University Montpellier, France
Impact of Automatic Feature Extraction in Deep Learning Architecture
Impact of Automatic Feature Extraction in Deep Learning Architecture Fatma Shaheen, Brijesh Verma and Md Asafuddoula Centre for Intelligent Systems Central Queensland University, Brisbane, Australia {f.shaheen,
DeCAF: 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
Teaching icub to recognize. objects. Giulia Pasquale. PhD student
Teaching icub to recognize RobotCub Consortium. All rights reservted. This content is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/. objects
Modeling the Contribution of Central Versus Peripheral Vision in Scene, Object, and Face Recognition
Modeling the Contribution of Central Versus Peripheral Vision in Scene, Object, and Face Recognition Panqu Wang (pawang@ucsd.edu) Department of Electrical and Engineering, University of California San
TRANSFORMING PHOTOS TO COMICS USING CONVOLUTIONAL NEURAL NETWORKS. Tsinghua University, China Cardiff University, UK
TRANSFORMING PHOTOS TO COMICS USING CONVOUTIONA NEURA NETWORKS Yang Chen Yu-Kun ai Yong-Jin iu Tsinghua University, China Cardiff University, UK ABSTRACT In this paper, inspired by Gatys s recent work,
GESTURE RECOGNITION FOR ROBOTIC CONTROL USING DEEP LEARNING
2017 NDIA GROUND VEHICLE SYSTEMS ENGINEERING AND TECHNOLOGY SYMPOSIUM AUTONOMOUS GROUND SYSTEMS (AGS) TECHNICAL SESSION AUGUST 8-10, 2017 - NOVI, MICHIGAN GESTURE RECOGNITION FOR ROBOTIC CONTROL USING
Deep 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:
Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks
Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks Jo rg Wagner1,2, Volker Fischer1, Michael Herman1 and Sven Behnke2 1- Robert Bosch GmbH - 70442 Stuttgart - Germany 2-
EE-559 Deep learning 7.2. Networks for image classification
EE-559 Deep learning 7.2. Networks for image classification François Fleuret https://fleuret.org/ee559/ Fri Nov 16 22:58:34 UTC 2018 ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE Image classification, standard
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions Hongyang Gao Texas A&M University College Station, TX hongyang.gao@tamu.edu Zhengyang Wang Texas A&M University
Compact Deep Convolutional Neural Networks for Image Classification
1 Compact Deep Convolutional Neural Networks for Image Classification Zejia Zheng, Zhu Li, Abhishek Nagar 1 and Woosung Kang 2 Abstract Convolutional Neural Network is efficient in learning hierarchical
ECS 289G UC Davis Paper Presenta6on #1
ECS 289G UC Davis Paper Presenta6on #1 ImageNet Classifica6on with Deep Convolu6onal Neural Networks Mohammad Motamedi Mohammad Motamedi ECS 289G PAPER PRESENTATION - UC DAVIS 1 Convolu6onal Neural Networks
Can you tell a face from a HEVC bitstream?
Can you tell a face from a HEVC bitstream? Saeed Ranjbar Alvar, Hyomin Choi and Ivan V. Bajić School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada Email: {saeedr,chyomin, ibajic}@sfu.ca
En 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
ROAD 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
arxiv: v1 [cs.ce] 9 Jan 2018
![arxiv: v1 [cs.ce] 9 Jan 2018](/thumbs/77/76232406.jpg "arxiv: v1 [cs.ce] 9 Jan 2018")
Predict Forex Trend via Convolutional Neural Networks Yun-Cheng Tsai, 1 Jun-Hao Chen, 2 Jun-Jie Wang 3 arxiv:1801.03018v1 [cs.ce] 9 Jan 2018 1 Center for General Education 2,3 Department of Computer Science
clcnet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
clcnet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions Dong-Qing Zhang ImaginationAI LLC dongqing@gmail.com Abstract Depthwise convolution and grouped convolution
arxiv: v1 [cs.cv] 15 Apr 2016
![arxiv: v1 [cs.cv] 15 Apr 2016](/thumbs/80/81898948.jpg "arxiv: v1 [cs.cv] 15 Apr 2016")
High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks arxiv:1604.04339v1 [cs.cv] 15 Apr 2016 Zifeng Wu, Chunhua Shen, Anton van den Hengel The University of Adelaide, SA 5005,
ECE 599/692 Deep Learning Lecture 19 Beyond BP and CNN
ECE 599/692 Deep Learning Lecture 19 Beyond BP and CNN Hairong Qi, Gonzalez Family Professor Electrical Engineering and Computer Science University of Tennessee, Knoxville http://www.eecs.utk.edu/faculty/qi
Introduction to Computer Engineering
Introduction to Computer Engineering Mohammad Hossein Manshaei manshaei@gmail.com Textbook Computer Science an Overview J.Glenn Brooksher, 11 th Edition Pearson 2011 2 Contents 1. Computer science vs computer
Convolutional 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
Object Recognition with and without Objects
Object Recognition with and without Objects Zhuotun Zhu, Lingxi Xie, Alan Yuille Johns Hopkins University, Baltimore, MD, USA {zhuotun, 198808xc, alan.l.yuille}@gmail.com Abstract While recent deep neural
Research 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:
Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising
Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising Peng Liu University of Florida pliu1@ufl.edu Ruogu Fang University of Florida ruogu.fang@bme.ufl.edu arxiv:177.9135v1 [cs.cv]
Colorful Image Colorizations Supplementary Material
Colorful Image Colorizations Supplementary Material Richard Zhang, Phillip Isola, Alexei A. Efros {rich.zhang, isola, efros}@eecs.berkeley.edu University of California, Berkeley 1 Overview This document
Visualizing and Understanding. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 12 -
Lecture 12: Visualizing and Understanding Lecture 12-1 May 16, 2017 Administrative Milestones due tonight on Canvas, 11:59pm Midterm grades released on Gradescope this week A3 due next Friday, 5/26 HyperQuest
Hand Gesture Recognition by Means of Region- Based Convolutional Neural Networks
Contemporary Engineering Sciences, Vol. 10, 2017, no. 27, 1329-1342 HIKARI Ltd, www.m-hikari.com https://doi.org/10.12988/ces.2017.710154 Hand Gesture Recognition by Means of Region- Based Convolutional
arxiv: v1 [cs.ne] 16 Nov 2016
![arxiv: v1 [cs.ne] 16 Nov 2016](/thumbs/77/75733598.jpg "arxiv: v1 [cs.ne] 16 Nov 2016")
Training Spiking Deep Networks for Neuromorphic Hardware arxiv:1611.5141v1 [cs.ne] 16 Nov 16 Eric Hunsberger Centre for Theoretical Neuroscience University of Waterloo Waterloo, ON N2L 3G1 ehunsber@uwaterloo.ca
Computer Vision Seminar
Computer Vision Seminar 236815 Spring 2017 Instructor: Micha Lindenbaum (Taub 600, Tel: 4331, email: mic@cs) Student in this seminar should be those interested in high level, learning based, computer vision.
CROSS-LAYER FEATURES IN CONVOLUTIONAL NEURAL NETWORKS FOR GENERIC CLASSIFICATION TASKS. Kuan-Chuan Peng and Tsuhan Chen
CROSS-LAYER FEATURES IN CONVOLUTIONAL NEURAL NETWORKS FOR GENERIC CLASSIFICATION TASKS Kuan-Chuan Peng and Tsuhan Chen Cornell University School of Electrical and Computer Engineering Ithaca, NY 14850
Introduction 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
arxiv: v1 [cs.sd] 1 Oct 2016
![arxiv: v1 [cs.sd] 1 Oct 2016](/thumbs/94/121674509.jpg "arxiv: v1 [cs.sd] 1 Oct 2016")
VERY DEEP CONVOLUTIONAL NEURAL NETWORKS FOR RAW WAVEFORMS Wei Dai*, Chia Dai*, Shuhui Qu, Juncheng Li, Samarjit Das {wdai,chiad}@cs.cmu.edu, shuhuiq@stanford.edu, {billy.li,samarjit.das}@us.bosch.com arxiv:1610.00087v1
Pelee: A Real-Time Object Detection System on Mobile Devices
Pelee: A Real-Time Object Detection System on Mobile Devices Robert J. Wang, Xiang Li, Shuang Ao & Charles X. Ling Department of Computer Science University of Western Ontario London, Ontario, Canada,
TripNet: Detecting Trip Hazards on Construction Sites
TripNet: Detecting Trip Hazards on Construction Sites Sean McMahon, Niko Sünderhauf, Michael Milford, Ben Upcroft ARC Centre of Excellence for Robotic Vision Queensland University of Technology (QUT),
A Deep Learning Approach To Universal Image Manipulation Detection Using A New Convolutional Layer
A Deep Learning Approach To Universal Image Manipulation Detection Using A New Convolutional Layer ABSTRACT Belhassen Bayar Drexel University Dept. of ECE Philadelphia, PA, USA bb632@drexel.edu When creating
What Is And How Will Machine Learning Change Our Lives. Fair Use Agreement
What Is And How Will Machine Learning Change Our Lives Raymond Ptucha, Rochester Institute of Technology 2018 Engineering Symposium April 24, 2018, 9:45am Ptucha 18 1 Fair Use Agreement This agreement
A Fast Method for Estimating Transient Scene Attributes
A Fast Method for Estimating Transient Scene Attributes Ryan Baltenberger, Menghua Zhai, Connor Greenwell, Scott Workman, Nathan Jacobs Department of Computer Science, University of Kentucky {rbalten,
Automatic understanding of the visual world
Automatic understanding of the visual world 1 Machine visual perception Artificial capacity to see, understand the visual world Object recognition Image or sequence of images Action recognition 2 Machine
Learning Deep Networks from Noisy Labels with Dropout Regularization
Learning Deep Networks from Noisy Labels with Dropout Regularization Ishan Jindal, Matthew Nokleby Electrical and Computer Engineering Wayne State University, MI, USA Email: {ishan.jindal, matthew.nokleby}@wayne.edu
arxiv: v5 [cs.cv] 23 Aug 2017
![arxiv: v5 [cs.cv] 23 Aug 2017](/thumbs/83/88579271.jpg "arxiv: v5 [cs.cv] 23 Aug 2017")
DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows arxiv:111.555v5 [cs.cv] 3 Aug 17 Jason Kuen 1 jkuen1@ntu.edu.sg Xiangfei Kong 1 xfkong@ntu.edu.sg Gang Wang gangwang@gmail.com
LANDMARK recognition is an important feature for
1 NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks Chakkrit Termritthikun, Surachet Kanprachar, Paisarn Muneesawang arxiv:1810.01074v1 [cs.cv] 2 Oct 2018 Abstract The growth
Correlating Filter Diversity with Convolutional Neural Network Accuracy
Correlating Filter Diversity with Convolutional Neural Network Accuracy Casey A. Graff School of Computer Science and Engineering University of California San Diego La Jolla, CA 92023 Email: cagraff@ucsd.edu
Recognition: Overview. Sanja Fidler CSC420: Intro to Image Understanding 1/ 83
Recognition: Overview Sanja Fidler CSC420: Intro to Image Understanding 1/ 83 Textbook This book has a lot of material: K. Grauman and B. Leibe Visual Object Recognition Synthesis Lectures On Computer
Toward Autonomous Mapping and Exploration for Mobile Robots through Deep Supervised Learning
Toward Autonomous Mapping and Exploration for Mobile Robots through Deep Supervised Learning Shi Bai, Fanfei Chen and Brendan Englot Abstract We consider an autonomous mapping and exploration problem in
arxiv: v1 [cs.lg] 2 Jan 2018
![arxiv: v1 [cs.lg] 2 Jan 2018](/thumbs/89/98840529.jpg "arxiv: v1 [cs.lg] 2 Jan 2018")
Deep Learning for Identifying Potential Conceptual Shifts for Co-creative Drawing arxiv:1801.00723v1 [cs.lg] 2 Jan 2018 Pegah Karimi pkarimi@uncc.edu Kazjon Grace The University of Sydney Sydney, NSW 2006
Recognition: Overview. Sanja Fidler CSC420: Intro to Image Understanding 1/ 78
Recognition: Overview Sanja Fidler CSC420: Intro to Image Understanding 1/ 78 Textbook This book has a lot of material: K. Grauman and B. Leibe Visual Object Recognition Synthesis Lectures On Computer
arxiv: v1 [cs.cv] 27 Nov 2016
![arxiv: v1 [cs.cv] 27 Nov 2016](/thumbs/72/66770659.jpg "arxiv: v1 [cs.cv] 27 Nov 2016")
Real-Time Video Highlights for Yahoo Esports arxiv:1611.08780v1 [cs.cv] 27 Nov 2016 Yale Song Yahoo Research New York, USA yalesong@yahoo-inc.com Abstract Esports has gained global popularity in recent
Radio 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
Artistic Image Colorization with Visual Generative Networks
Artistic Image Colorization with Visual Generative Networks Final report Yuting Sun ytsun@stanford.edu Yue Zhang zoezhang@stanford.edu Qingyang Liu qnliu@stanford.edu 1 Motivation Visual generative models,
Image 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
Tiny 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
arxiv: v2 [cs.sd] 22 May 2017
![arxiv: v2 [cs.sd] 22 May 2017](/thumbs/72/66381162.jpg "arxiv: v2 [cs.sd] 22 May 2017")
SAMPLE-LEVEL DEEP CONVOLUTIONAL NEURAL NETWORKS FOR MUSIC AUTO-TAGGING USING RAW WAVEFORMS Jongpil Lee Jiyoung Park Keunhyoung Luke Kim Juhan Nam Korea Advanced Institute of Science and Technology (KAIST)
Sketch-a-Net that Beats Humans
Sketch-a-Net that Beats Humans Qian Yu SketchLab@QMUL Queen Mary University of London 1 Authors Qian Yu Yongxin Yang Yi-Zhe Song Tao Xiang Timothy Hospedales 2 Let s play a game! Round 1 Easy fish face
An 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/
Value-added Applications with Deep Learning. src:
SMART TOURISM Value-added Applications with Deep Learning src: https://www.wttc.org/-/media/files/reports/economic-impact-research/countries-2017/thailand2017.pdf Somnuk Phon-Amnuaisuk, Minh-Son Dao, CIE,
arxiv: v1 [cs.lg] 17 Jan 2019
![arxiv: v1 [cs.lg] 17 Jan 2019](/thumbs/93/114162819.jpg "arxiv: v1 [cs.lg] 17 Jan 2019")
Virtual-to-Real-World Transfer Learning for Robots on Wilderness Trails Michael L. Iuzzolino 1 and Michael E. Walker 2 and Daniel Szafir 3 arxiv:1901.05599v1 [cs.lg] 17 Jan 2019 Abstract Robots hold promise
Free-hand Sketch Recognition Classification
Free-hand Sketch Recognition Classification Wayne Lu Stanford University waynelu@stanford.edu Elizabeth Tran Stanford University eliztran@stanford.edu Abstract People use sketches to express and record
CS 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
GPU 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
Automated 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
Detection 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
Split-Complex Convolutional Neural Networks
Split-Complex Convolutional Neural Networks Timothy Anderson, 27 Timothy Anderson Department of Electrical Engineering Stanford University Stanford, CA 9435 timothy.anderson@stanford.edu Introduction Beginning
CONVOLUTIONAL 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
Spectral Detection and Localization of Radio Events with Learned Convolutional Neural Features
Spectral Detection and Localization of Radio Events with Learned Convolutional Neural Features Timothy J. O Shea Arlington, VA oshea@vt.edu Tamoghna Roy Blacksburg, VA tamoghna@vt.edu Tugba Erpek Arlington,
Wide Residual Networks
SERGEY ZAGORUYKO AND NIKOS KOMODAKIS: WIDE RESIDUAL NETWORKS 1 Wide Residual Networks Sergey Zagoruyko sergey.zagoruyko@enpc.fr Nikos Komodakis nikos.komodakis@enpc.fr Université Paris-Est, École des Ponts
arxiv: v1 [cs.ne] 11 Jun 2018
![arxiv: v1 [cs.ne] 11 Jun 2018](/thumbs/91/106982896.jpg "arxiv: v1 [cs.ne] 11 Jun 2018")
When and where do feed-forward neural networks learn localist representations? arxiv:1806.03934v1 [cs.ne] 11 Jun 2018 Ella M. Gale, Nicolas Martin & Jeffrey S. Bowers School of Experimental Psychology
REAL TIME EMULATION OF PARAMETRIC GUITAR TUBE AMPLIFIER WITH LONG SHORT TERM MEMORY NEURAL NETWORK
REAL TIME EMULATION OF PARAMETRIC GUITAR TUBE AMPLIFIER WITH LONG SHORT TERM MEMORY NEURAL NETWORK Thomas Schmitz and Jean-Jacques Embrechts 1 1 Department of Electrical Engineering and Computer Science,
MS-Celeb-1M: Challenge of Recognizing One Million Celebrities in the Real World
MS-Celeb-1M: Challenge of Recognizing One Million Celebrities in the Real World Yandong Guo, Lei Zhang, Yuxiao Hu, Xiaodong He, and Jianfeng Gao Microsoft; Redmond, WA 98052 Abstract Face recognition,
Draw and Tell: Multimodal Descriptions Outperform Verbal- or Sketch-Only Descriptions in an Image Retrieval Task
Draw and Tell: Multimodal Descriptions Outperform Verbal- or Sketch-Only Descriptions in an Image Retrieval Task Ting Han and David Schlangen Dialogue Systems Group // CITEC // Faculty of Linguistics and
A Deep Learning Approach for Wi-Fi based People Localization
A Deep Learning Approach for Wi-Fi based People Localization A. M. Khalili 1,*, Abdel-Hamid Soliman 1 and Md Asaduzzaman 1 1 School of Creative Arts and Engineering, Staffordshire University, United Kingdom;
Vehicle Color Recognition using Convolutional Neural Network
Vehicle Color Recognition using Convolutional Neural Network Reza Fuad Rachmadi and I Ketut Eddy Purnama Multimedia and Network Engineering Department, Institut Teknologi Sepuluh Nopember, Keputih Sukolilo,
arxiv: v1 [cs.cv] 30 Mar 2017
![arxiv: v1 [cs.cv] 30 Mar 2017](/thumbs/95/125122949.jpg "arxiv: v1 [cs.cv] 30 Mar 2017")
A Paradigm Shift: Detecting Human Rights Violations Through Web Images Grigorios Kalliatakis, Shoaib Ehsan, and Klaus D. McDonald-Maier arxiv:1703.10501v1 [cs.cv] 30 Mar 2017 School of Computer Science
Special Topics in Mechano InformaticsⅡ 2017/5/31
Special Topics in Mechano InformaticsⅡ 2017/5/31 Object class recognition Object detection Sports car Sports car Image caption generation A yellow train on the tracks near a train station. Semantic segmentation
Deep Learning Features at Scale for Visual Place Recognition
Deep Learning Features at Scale for Visual Place Recognition Zetao Chen, Adam Jacobson, Niko Sünderhauf, Ben Upcroft, Lingqiao Liu, Chunhua Shen, Ian Reid and Michael Milford 1 Figure 1 (a) We have developed
Lesson 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
arxiv: v1 [cs.cv] 23 May 2016
![arxiv: v1 [cs.cv] 23 May 2016](/thumbs/71/66054425.jpg "arxiv: v1 [cs.cv] 23 May 2016")
arxiv:1605.07146v1 [cs.cv] 23 May 2016 SERGEY ZAGORUYKO AND NIKOS KOMODAKIS: WIDE RESIDUAL NETWORKS 1 Wide Residual Networks Sergey Zagoruyko sergey.zagoruyko@enpc.fr Nikos Komodakis nikos.komodakis@enpc.fr
Comparing Time and Frequency Domain for Audio Event Recognition Using Deep Learning
Comparing Time and Frequency Domain for Audio Event Recognition Using Deep Learning Lars Hertel, Huy Phan and Alfred Mertins Institute for Signal Processing, University of Luebeck, Germany Graduate School
Adversarial examples in Deep Neural Networks. Luiz Gustavo Hafemann Le Thanh Nguyen-Meidine
Adversarial examples in Deep Neural Networks Luiz Gustavo Hafemann Le Thanh Nguyen-Meidine Agenda Introduction Attacks and Defenses NIPS 2017 adversarial attacks competition Demo Discussion 2 Introduction
Does Haze Removal Help CNN-based Image Classification?
Does Haze Removal Help CNN-based Image Classification? Yanting Pei 1,2, Yaping Huang 1,, Qi Zou 1, Yuhang Lu 2, and Song Wang 2,3, 1 Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing
Park Smart. D. Di Mauro 1, M. Moltisanti 2, G. Patanè 2, S. Battiato 1, G. M. Farinella 1. Abstract. 1. Introduction
Park Smart D. Di Mauro 1, M. Moltisanti 2, G. Patanè 2, S. Battiato 1, G. M. Farinella 1 1 Department of Mathematics and Computer Science University of Catania {dimauro,battiato,gfarinella}@dmi.unict.it
arxiv: v1 [cs.cv] 9 Nov 2015 Abstract
![arxiv: v1 [cs.cv] 9 Nov 2015 Abstract](/thumbs/87/97059916.jpg "arxiv: v1 [cs.cv] 9 Nov 2015 Abstract")
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding Alex Kendall Vijay Badrinarayanan University of Cambridge agk34, vb292, rc10001 @cam.ac.uk
Sketch-a-Net: a Deep Neural Network that Beats Humans
Sketch-a-Net: a Deep Neural Network that Beats Humans Yu, Q; Yang, Y; Liu, F; SONG, Y; Xiang, T; Hospedales, T DOI: 0.00/s-0-0- For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle//
Lecture 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
Food Image Recognition Using Deep Convolutional Network with Pre-training and Fine-tuning
Food Image Recognition Using Deep Convolutional Network with Pre-training and Fine-tuning ICME Workshop on Multimedia for Cooking and Eating Activities (CEA) July 3 th 2015 Keiji Yanai and Yoshiyuki Kawano
A 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
Analyzing features learned for Offline Signature Verification using Deep CNNs
Accepted as a conference paper for ICPR 2016 Analyzing features learned for Offline Signature Verification using Deep CNNs Luiz G. Hafemann, Robert Sabourin Lab. d imagerie, de vision et d intelligence
Generating 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
Project Title: Sparse Image Reconstruction with Trainable Image priors
Project Title: Sparse Image Reconstruction with Trainable Image priors Project Supervisor(s) and affiliation(s): Stamatis Lefkimmiatis, Skolkovo Institute of Science and Technology (Email: s.lefkimmiatis@skoltech.ru)
Adversarial Examples and Adversarial Training. Ian Goodfellow, OpenAI Research Scientist Presentation at HORSE 2016 London,
Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Presentation at HORSE 2016 London, 2016-09-19 In this presentation Intriguing Properties of Neural Networks Szegedy