very deep residual networks with maxout for plant
play

Very Deep Residual Networks with Maxout for Plant Identification in - PowerPoint PPT Presentation

Sep 08, 2023 •40 likes •190 views

Very Deep Residual Networks with Maxout for Plant Identification in the Wild Mi l a n u l c , Dmy t r o Mi s h k i n , J i Ma t a s C e n t e r f o r Ma c h i n e P e r c e p t i o n D

  1. Very Deep Residual Networks with Maxout for Plant Identification in the Wild Mi l a n Š u l c , Dmy t r o Mi s h k i n , J i ř í Ma t a s C e n t e r f o r Ma c h i n e P e r c e p t i o n D e p a r t m e n t o f C y b e r n e t i c s F a c u l t y o f E l e c t r i c a l E n g i n e e r i n g C z e c h T e c h n i c a l U n i v e r s i t y i n P r a g u e

  2. P l a n t Re c o g n i t i o n a t C MP b e f o r e C L E F ' 1 6 We w o r k e d o n n a r r o w e r p r o b l e m s w i t h h a n d - c r a f t e d f e a t u r e s w i t h s t a t e - o f - t h e - a r t r e s u l t s : ● B a r k r e c o g n i t i o n : t e x t u r a l d e s c r i p t i o n [ 1 ] ● L e a f r e c o g n i t i o n : d e s c r i b i n g t e x t u r e o f t h e l e a f i n t e r i o r a n d b o r d e r [ 2 ] [1] Kernel-mapped histograms of multi-scale LBPs for tree bark recognition. Milan Šulc and Jiří Matas. IVCNZ 2013. [2] Fast features invariant to rotation and scale of texture. Milan Šulc and Jiří Matas. ECCV 2014, CVPPP workshop. . 1 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  3. L e s s o n s f r o m p r e v i o u s P l a n t C L E F s ● B e s t p e r f o r m i n g d e s c r i p t o r s : ● S e p a r a t e n e t w o r k s f o r d i fg e r e n t c o n t e n t t y p e s d i d n ' t h e l p . ● S i g n i fj c a n t e fg e c t o f b a g g i n g . . 2 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  4. L e s s o n s f r o m C NN E v o l u t i o n ● R e s i d u a l N e t w o r k s [ 3 ] ( R e s N e t ) : B e s t r e s u l t s i n I L S V R C 2 0 1 5 a n d MS C O C O 2 0 1 5 . ● Ma x o u t [ 4 ] a c t i v a t i o n f u n c t i o n l o o k s p r o m i s s i n g , w h e n c o m b i n e d w i t h d r o p o u t f o r b e t t e r r e g u l a r i z a t i o n . [3] Deep Residual Learning for Image Recognition. Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun. CVPR 2016. [4] Maxout Networks. Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron C. Courville, and Yoshua Bengio. ICML (3) 28 (2013): 1319-1327. . 3 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  5. De e p Re s i d u a l Ne t w o r k s ● H e e t a l . [ 3 ] s h o w e d t h a t r e s i d u a l c o n n e c t i o n s a c c e l e r a t e l e a r n i n g e v e n f o r e x t r e m e l y d e e p n e t w o r k s . ● We b u i l d o n t h e R e s N e t - 1 5 2 m o d e l p r e - t r a i n e d o n I m a g e N e t . ● 8 x d e e p e r t h a n V G G - 1 9 [ 5 ] , b u t s t i l l l o w e r c o m p l e x i t y . V G G - 1 9 : 1 9 . 6 b i l l i o n F L O P s . R e s N e t - 1 5 2 :1 1 . 3 b i l l i o n F L O P s . [3] Deep Residual Learning for Image Recognition. Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun. CVPR 2016. [5] Very deep convolutional networks for large-scale image recognition. Karen Simonyan and Andrew Zisserman. arXiv preprint arXiv:1409.1556 (2014). . 4 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  6. T h e Ma x o u t ● Ma x o u t [ 4 ] u n i t : ~ n e t w o r k a c t i v a t i o n f u n c t i o n . ● D r o p o u t i s p e r f o r m e d o n , b e f o r e m u l t i p l i c a t i o n b y x w e i g h t s . [4] Maxout Networks. Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron C. Courville, and Yoshua Bengio. ICML (3) 28 (2013): 1319-1327. . 5 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  7. T h e Ma x o u t ● A s i n g l e Ma x o u t [ 4 ] u n i t c a n b e i n t e r p r e t e d a s m a k i n g a p i e c e w i s e l i n e a r a p p r o x i m a t i o n t o a n y c o n v e x f u n c t i o n . [4] Maxout Networks. Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron C. Courville, and Yoshua Bengio. ICML (3) 28 (2013): 1319-1327. . 6 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  8. C MP Ne t w o r k : Re s Ne t - 1 5 2 w i t h Ma x o u t ● R e s N e t - 1 5 2 p r e - t r a i n e d o n I m a g e N e t . ● F C l a y e r r e p l a c e d b y 4 p i e c e s o f F C l a y e r s , 5 1 2 n e u r o n s e a c h , f o l l o w e d w i t h Ma x o u t . ● D r o p o u t i s p e r f o r m e d o n t h e i n p u t s o f t h e F C l a y e r s . ● A n o t h e r F C l a y e r i s a d d e d o n t h e t o p f o r c l a s s i fj c a t i o n . . 7 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  9. P r e l i mi n a r y E x p e r i me n t s ● T r a i n i n g s e t : 2 0 1 5 t r a i n i n g d a t a . ● V a l i d a t i o n s e t :2 0 1 5 t e s t d a t a . . 8 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  10. C MP S u b mi s s i o n s ● C MP R u n 1 ( m a i n s u b m i s s i o n ) : ● B a g g i n g o f 3 n e t w o r k s ( R e s N e t - 1 5 2 + Ma x O u t ) . ● P l a n t C L E F 2 0 1 6 t r a i n i n g s e t d i v i d e d i n t o 3 f o l d s , e a c h n e t w o r k u s e s 2 f o l d s f o r t r a i n i n g . ● F i n e - t u n i n g f o r 1 1 0 K i t e r a t i o n s ( d u e t o l i m i t e d t i m e ) . ● C MP R u n 2 : ● O n l y o n e o f t h e t h r e e n e t w o r k s . ● C MP R u n 3 : ● N e t w o r k fj n e - t u n e d i n p r e l i m i n a r y e x p e r i m e n t s o n P l a n t C L E F 2 0 1 5 t r a i n i n g d a t a , 3 7 0 K i t e r a t i o n s . . 9 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

  11. Offjc i a l S c o r e : Me a n A v e r a g e P r e c i s i o n . 10 C L E F 2 0 1 6 M. Š u l c , D . Mi s h k i n , J . Ma t a s : V e r y D e e p R e s i d u a l N e t w o r k s w i t h Ma x O u t f o r P l a n t I d e n t i fj c a t i o n i n t h e Wi l d

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

ReLu and Maxout Networks and Their Possible Connections to Tropical Methods J org Zimmermann,

ReLu and Maxout Networks and Their Possible Connections to Tropical Methods J org Zimmermann,

ReLu and Maxout Networks and Their Possible Connections to Tropical Methods J org Zimmermann, AG Weber Institute of Computer Science University of Bonn, Germany 1 J org Zimmermann: ReLu and Maxout Networks and Their Possible Connections

542 views • 16 slides
An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning Microsoft Research Asia (MSRA) Kaiming He, Xiangyu Zhang, Shaoqing Ren, & Jian Sun. Deep Residual Learning for Image Recognition. arXiv

1.32k views • 54 slides
AMMI Introduction to Deep Learning 6.5. Residual networks Fran cois Fleuret

AMMI Introduction to Deep Learning 6.5. Residual networks Fran cois Fleuret

AMMI Introduction to Deep Learning 6.5. Residual networks Fran cois Fleuret https://fleuret.org/ammi-2018/ Fri Nov 9 22:38:28 UTC 2018 COLE POLYTECHNIQUE FDRALE DE LAUSANNE Residual networks Fran cois Fleuret AMMI

732 views • 36 slides
Reduced-memory training and deployment of deep residual networks by stochastic binary quantization

Reduced-memory training and deployment of deep residual networks by stochastic binary quantization

Reduced-memory training and deployment of deep residual networks by stochastic binary quantization Mark D. McDonnell 1 , Ruchun Wang 2 and Andr van Schaik 2 cls-lab.org 2 BENS Laboratory 1 Computational Learning Systems Laboratory MARCS

256 views • 23 slides
Deep Learning for Predictive Maintenance Pawel Morkisz GTC 2017 Agenda Problem

Deep Learning for Predictive Maintenance Pawel Morkisz GTC 2017 Agenda Problem

Deep Learning for Predictive Maintenance Pawel Morkisz GTC 2017 Agenda Problem Introduction and notion of deep neural networks o Convolutional layers o Residual networks (ResNet) One dimensional convolutional networks in failure

276 views • 23 slides
Pipeline Strategies and conversations behind securing a Residual Bequest Agenda 1. Why Residual?

Pipeline Strategies and conversations behind securing a Residual Bequest Agenda 1. Why Residual?

The Perpetual Pipeline Strategies and conversations behind securing a Residual Bequest Agenda 1. Why Residual? 2. Structured for Residual 3. Residual Results 4. Residual Strategy 5. Residual Relationships 6. Residual Data 7.

1.17k views • 43 slides
Residual Networks (ResNet) Residual Networks (ResNet) In [1]: import d2l from mxnet import gluon,

Residual Networks (ResNet) Residual Networks (ResNet) In [1]: import d2l from mxnet import gluon,

3/8/2019 resnet slides Residual Networks (ResNet) Residual Networks (ResNet) In [1]: import d2l from mxnet import gluon, init, nd from mxnet.gluon import nn http://127.0.0.1:8000/resnet.slides.html?print-pdf/#/ 1/10 3/8/2019 resnet slides

890 views • 10 slides
Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations deeplearning.cce2020@gmail.com Deep Networks Intuition Neural networks with multiple hidden layers - Deep networks [Hinton, 2006] Deep Networks Intuition

1.33k views • 28 slides
Highway Networks and Residual Networks Renjie Liao University of Toronto Jan 26, 2016 Renjie

Highway Networks and Residual Networks Renjie Liao University of Toronto Jan 26, 2016 Renjie

Highway Networks and Residual Networks Renjie Liao University of Toronto Jan 26, 2016 Renjie Liao (UofT) Highway Networks and Residual Networks Jan 26, 2016 1 / 23 Neural Network A network connecting numerous neurons Renjie Liao (UofT)

685 views • 40 slides
Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan Zelener Machine Learning Reading Group January 7 th 2016 The Graduate Center, CUNY Objectives Explain some of the trends of deep learning and

680 views • 44 slides
Deep Networks Andrea Passerini passerini@disi.unitn.it Machine Learning Deep Networks Need for

Deep Networks Andrea Passerini passerini@disi.unitn.it Machine Learning Deep Networks Need for

Deep Networks Andrea Passerini passerini@disi.unitn.it Machine Learning Deep Networks Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels

563 views • 43 slides
Deep Networks Andrea Passerini passerini@disi.unitn.it Machine Learning Deep Networks Need for

Deep Networks Andrea Passerini passerini@disi.unitn.it Machine Learning Deep Networks Need for

Deep Networks Andrea Passerini passerini@disi.unitn.it Machine Learning Deep Networks Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels

1.45k views • 34 slides
Deep Residual Learning for Portfolio Optimization: With Attention and Switching Modules Jeff

Deep Residual Learning for Portfolio Optimization: With Attention and Switching Modules Jeff

Deep Residual Learning for Portfolio Optimization: With Attention and Switching Modules Jeff Wang, Ph.D. Prepared for NYU FRE Seminar. March 7th, 2019 1 / 48 Overview Study model driven portfolio management strategies Construct

694 views • 48 slides
Residual Flows for Invertible Generative Modeling Ricky T. Q. Chen, Jens Behrmann, David

Residual Flows for Invertible Generative Modeling Ricky T. Q. Chen, Jens Behrmann, David

Residual Flows for Invertible Generative Modeling Ricky T. Q. Chen, Jens Behrmann, David Duvenaud, Jrn-Henrik Jacobsen Invertible Residual Networks (i-ResNet) It can be shown that residual blocks can be inverted by fixed-point iteration and

442 views • 16 slides
EISI Plant-Pollinator Networks 2017 1. Jane S. Huestis Phylogenetics of plant-pollinator

EISI Plant-Pollinator Networks 2017 1. Jane S. Huestis Phylogenetics of plant-pollinator

EISI Plant-Pollinator Networks 2017 1. Jane S. Huestis Phylogenetics of plant-pollinator networks 1. Andrew N. Guide Pollinator preferences 1. Elaina G. Thomas Beta diversity in montane meadows 1. Lydia S. Miller Modularity of

159 views • 12 slides
Deep Residual Learning for Image Recognition Kaiming He et al. (Microsoft Research) By Zana

Deep Residual Learning for Image Recognition Kaiming He et al. (Microsoft Research) By Zana

2017-11-15 Deep Residual Learning for Image Recognition Kaiming He et al. (Microsoft Research) By Zana Rashidi (MSc student, York University) Introduction 1 2017-11-15 ILSVRC & COCO 2015 Competitions 1st place in all five main tracks :

480 views • 19 slides
if H has a b reak p oint k m H ( N ) Hoeffding Inequality Union Bound VC Bound

if H has a b reak p oint k m H ( N ) Hoeffding Inequality Union Bound VC Bound

Review of Leture 6 The V C Inequalit y is p olynomial if H has a b reak p oint k m H ( N ) Hoeffding Inequality Union Bound VC Bound space of k data sets 1 2 3 4 5 6 . . . 1 1 2 2 2 2 2 . . D 2

530 views • 25 slides
CHRO Circle Virtual Discussion February 2020 Facilitor: Edie L. Goldberg, Ph.D. The Inside Gig

CHRO Circle Virtual Discussion February 2020 Facilitor: Edie L. Goldberg, Ph.D. The Inside Gig

CHRO Circle Virtual Discussion February 2020 Facilitor: Edie L. Goldberg, Ph.D. The Inside Gig Edie L. Goldberg, Ph.D. HRPS CHRO Circle 02/04/2020 The Need to Continuously Learn and Grow 5 years 8 of 10 93 % 1 of 3 42 % Half-Life of

267 views • 10 slides
JUST THE MATHS SLIDES NUMBER 8.2 VECTORS 2 (Vectors in component form) by A.J.Hobson

JUST THE MATHS SLIDES NUMBER 8.2 VECTORS 2 (Vectors in component form) by A.J.Hobson

JUST THE MATHS SLIDES NUMBER 8.2 VECTORS 2 (Vectors in component form) by A.J.Hobson 8.2.1 The components of a vector 8.2.2 The magnitude of a vector in component form 8.2.3 The sum and difference of vectors in component form 8.2.4

273 views • 9 slides
Distillation of quantum coherence ( 1711.10512 & 1804.09500 ) Kun Fang 1 RMS:QI workshop 2018,

Distillation of quantum coherence ( 1711.10512 & 1804.09500 ) Kun Fang 1 RMS:QI workshop 2018,

Distillation of quantum coherence ( 1711.10512 & 1804.09500 ) Kun Fang 1 RMS:QI workshop 2018, JILA Based on joint works with Gerardo Adesso 2 , Ludovico Lami 2 , Bartosz Regula 2 , Xin Wang 1 1 Centre for Quantum Software and Information

733 views • 38 slides
Mining Temporal Invariants from Partially Ordered Logs Ivan Beschastnikh Yuriy Brun University

Mining Temporal Invariants from Partially Ordered Logs Ivan Beschastnikh Yuriy Brun University

Mining Temporal Invariants from Partially Ordered Logs Ivan Beschastnikh Yuriy Brun University of Washington Michael D. Ernst Arvind Krishnamurthy Thomas E. Anderson Motivating question I am a developer. Why does my system behave in a

774 views • 38 slides
GAN Foundations CSC2541 Michael Chiu - chiu@cs.toronto.edu Jonathan Lorraine -

GAN Foundations CSC2541 Michael Chiu - chiu@cs.toronto.edu Jonathan Lorraine -

GAN Foundations CSC2541 Michael Chiu - chiu@cs.toronto.edu Jonathan Lorraine - Lorraine@cs.toronto.edu Ali Punjani - alipunjani@cs.toronto.edu Michael Tao - mtao@dgp.toronto.edu Basic Algorithm Generative Models Three major tasks, given a

669 views • 34 slides
The CalderoChapoton formula as a dimer partition function joint work with lke anak and

The CalderoChapoton formula as a dimer partition function joint work with lke anak and

The CalderoChapoton formula as a dimer partition function joint work with lke anak and Alastair King Matthew Pressland Universitt Stuttgart Tropical Geometry Meets Representation Theory, Universitt zu Kln Matthew Pressland

343 views • 10 slides
Universality for the dimer model Nathana el Berestycki University of Cambridge with Benoit

Universality for the dimer model Nathana el Berestycki University of Cambridge with Benoit

Universality for the dimer model Nathana el Berestycki University of Cambridge with Benoit Laslier (Paris) and Gourab Ray (Cambridge) Les Diablerets, February 2017 The dimer model Definition G = bipartite finite graph, planar Dimer

835 views • 30 slides

More recommend