active learning co training 3 subtract average detection
play

Active learning Co-training 3 Subtract-average detection score - PowerPoint PPT Presentation

Sep 25, 2023 •284 likes •611 views

Active learning Co-training 3 Subtract-average detection score Grey-scale detection score Summary Boosting is a method for learning an accurate classifiers by combining many weak classifiers. Boosting is resistant to over-fitting .

  1. Active learning

  2. Co-training

  3. 3

  4. Subtract-average detection score Grey-scale detection score

  5. Summary • Boosting is a method for learning an accurate classifiers by combining many weak classifiers. • Boosting is resistant to over-fitting . • Margins quantify prediction confidence. • High noise is a serious problem for learning classifiers- can’t be solved by minimizing convex functions. • Robustboost can solve some high noise problems. Exact characterization still unclear. • Jboost - an implementation of ADTrees and various boosting algorithms in java. • Book on boosting coming this spring. • Thank you, questions? 5

  6. Pedestrian detection - typical segment 5/17/06 UCLA

  7. Current best results 5/17/06 UCLA

  8. Image Features “Rectangle filters” Similar to Haar wavelets Papageorgiou, et al. ⎧ h t ( x i ) = 1 if f t ( x i ) > θ t ⎨ ⎩ 0 otherwise Very fast to compute using “integral image”. Unique Binary Features Combined using adaboost 5/17/06 UCLA

  9. Yotam’s features max (p1,p2) < min(q1,q2,q3,q4) Faster to calculate than Viola and Jones Search for a good feature based on genetic programming 5/17/06 UCLA

  10. Definition •Feature works in one of 3 resolutions: full, half, quarter •Two sets of up to 6 points each •Each point is an individual pixel •Feature says yes if all white points have higher values then all black points, or vice versa 5/17/06 UCLA

  11. Advantages • Deal better with the variation in illumination, no need to normalize. • Highly efficient (3-4 image access operations). 2 times faster than Viola&Jones • 20% of the memory 5/17/06 UCLA

  12. Steps of batch learning • Collect labeled examples • Run learning algorithm to generate classification rule • Test classification rule on new data. 5/17/06 UCLA

  13. Labeling process 1500 pedestrians Collected 6 Hrs of video -> 540,000 frames 170,000 boxes per frame 20 seconds for marking a box around a pedestrian. 3 seconds for deciding if box is pedestrian or not. How to choose “hard” negative examples? 5/17/06 UCLA

  14. Steps of active learning • Collect labeled examples • Run learning algorithm to generate classification rule • Apply classifier on new data. 
 and 
 label informative examples. 5/17/06 UCLA

  15. SEVILLE screen shot 1 5/17/06 UCLA

  16. SEVILLE screen shot 2 5/17/06 UCLA

  17. Margins Consider the following: An example: <x,y> e.g. < ,+1> ∑ Normalized score: ( ) T α t h t x − 1 ≤ ≤ 1 t = 1 ∑ T α t t = 1 ∑ ( ) T α t h t x The margin is: t = 1 y ∑ T α t t = 1 margin > 0 means correct classification 5/17/06 UCLA

  18. Display the rectangles inside the margins 5/17/06 UCLA

  19. large margins => reliable predictions 1000 2000 3000 10 20 50 100 500 Validation Learning 0 0.5 1 0 0.5 1 5/17/06 UCLA

  20. Margin Distributions 5/17/06 UCLA

  21. Summary of Training effort 5/17/06 UCLA

  22. Summary of Training Only examples whose score is in this range are hand - labeled 5/17/06 UCLA

  23. Few training examples 5/17/06 UCLA

  24. After re-labeling feedback 5/17/06 UCLA

  25. Final detector 5/17/06 UCLA

  26. Examples - easy Positive Negative 5/17/06 UCLA

  27. Examples - medium Positive Negative 5/17/06 UCLA

  28. Examples - hard Iteration Positive Negative 7 8 9 10 5/17/06 UCLA

  29. And the figure in the gown is.. 5/17/06 UCLA

  30. Seville cycles 5/17/06 UCLA

  31. Summary • Boosting and SVM control over-fitting using margins. • Margins measure the stability of the prediction, not conditional probability. • Margins are useful for co-training and for active-learning. 31 5/17/06 UCLA

Recommend

Agenda Intro to Active Learning Activity Design Resources for Active Learning Lunch with Active

Agenda Intro to Active Learning Activity Design Resources for Active Learning Lunch with Active

Agenda Intro to Active Learning Activity Design Resources for Active Learning Lunch with Active Learning Veterans Wrap Up Introduction to Active Learning What is active learning? Brainstorm your ideas with your group and generate a

855 views • 42 slides
Multi-Task Active Learning Yi Zhang Outline Active Learning Multi-Task Active Learning

Multi-Task Active Learning Yi Zhang Outline Active Learning Multi-Task Active Learning

Multi-Task Active Learning Yi Zhang Outline Active Learning Multi-Task Active Learning Linguistic Annotations (ACL 08) Image Classification (CVPR 08) Current Work and Discussions Constraint-Driven Active Learning

945 views • 47 slides
An Empirical Study on Selective Sampling in Active Learning for Splog Detection Taichi Katayama 1

An Empirical Study on Selective Sampling in Active Learning for Splog Detection Taichi Katayama 1

An Empirical Study on Selective Sampling in Active Learning for Splog Detection Taichi Katayama 1 Takehito Utsuro 1 Yuuki Sato 2 Takayuki Yoshinaka 3 Yasuhide Kawada 4 Tomohiro Fukuhara 5 1 University of Tsukuba, 2 Konami Corporation, 3 Tokyo Denki

661 views • 44 slides
ACTIVE 1. WELCOME and JUMPING IN LEARNING 1. WHAT IS ACTIVE LEARNING? la Carte 1.

ACTIVE 1. WELCOME and JUMPING IN LEARNING 1. WHAT IS ACTIVE LEARNING? la Carte 1.

ACTIVE 1. WELCOME and JUMPING IN LEARNING 1. WHAT IS ACTIVE LEARNING? la Carte 1. CONSTRUCTING our TEACHING CHALLENGES in a low tech 1. ORCHESTRATION environment 1. SHOW-AND-TELL Selma Hamdani Psychology / DALC / Neuroscience

836 views • 50 slides
Active Learning Passive Learning Active Learning 1. Think 1. Acquisition of knowledge Ability

Active Learning Passive Learning Active Learning 1. Think 1. Acquisition of knowledge Ability

Active Learning Passive Learning Active Learning 1. Think 1. Acquisition of knowledge Ability 2. Decision making 2. Application of knowledge 3. Explain/communicate 1. Deep learning Approach to Uni-directional 2. Interactive Learning

282 views • 5 slides
Fractions and Proportion Learning Objective: To be able to add and subtract fractions with a

Fractions and Proportion Learning Objective: To be able to add and subtract fractions with a

Fractions and Proportion Learning Objective: To be able to add and subtract fractions with a common denominator. www.planbee.com 9 7 + = 10 10 How could you find the answer to the question? Do you know what the answer is?

393 views • 26 slides
Maths week commencing 12.10.20 Week Overview of learning: Bonds to 100 (tens) Add/subtract 1's

Maths week commencing 12.10.20 Week Overview of learning: Bonds to 100 (tens) Add/subtract 1's

Y2 Maths teaching slides week of 12.10.20.notebook October 11, 2020 Maths week commencing 12.10.20 Week Overview of learning: Bonds to 100 (tens) Add/subtract 1's 10 more/10 less add/subtract 10's Add my making tens Y2 Maths teaching slides

1.11k views • 42 slides
Training neural networks Today's lecture Learning from small data Curriculum: Active

Training neural networks Today's lecture Learning from small data Curriculum: Active

Training neural networks Today's lecture Learning from small data Curriculum: Active learning - How transferable are features in deep neural When you are not learning networks? Surrogat losses

1k views • 69 slides
12.1 Active Learning: A Review When learning, it may be the case that getting the true labels of

12.1 Active Learning: A Review When learning, it may be the case that getting the true labels of

CS/CNS/EE 253: Advanced Topics in Machine Learning Topic: Active Learning Review and Kernel Methods Lecturer: Andreas Krause Scribe: Jonathan Krause Date: Feb. 17, 2010 12.1 Active Learning: A Review When learning, it may be the case that getting

213 views • 5 slides
Predator and Prey: Active Learning Is Social Learning Kenneth Ronkowitz Active Learning

Predator and Prey: Active Learning Is Social Learning Kenneth Ronkowitz Active Learning

Predator and Prey: Active Learning Is Social Learning Kenneth Ronkowitz Active Learning Symposium, Rutgers University, May 15, 2018 Typically part of the curriculum in biology, phrenology, biology, anatomy, craniometry, physiognomy, crime

484 views • 14 slides
Learning Loss for Active Learning Rymarczyk D., Zieliski B., Tabor J., Sadowski M., Titov M.

Learning Loss for Active Learning Rymarczyk D., Zieliski B., Tabor J., Sadowski M., Titov M.

Learning Loss for Active Learning Rymarczyk D., Zieliski B., Tabor J., Sadowski M., Titov M. Agenda 1. Active Learning introduction 2. Base methods in AL for Deep Learning 3. Learning Loss for Active Learning 4. Our ideas for Active

802 views • 43 slides
10.1 Active Learning Review What questions should be asked in order to collect best data?

10.1 Active Learning Review What questions should be asked in order to collect best data?

CS/CNS/EE 253: Advanced Topics in Machine Learning Topic: Active Learning 2: the myopic version-space shrinking strategy Lecturer: Daniel Golovin Scribe: Pete Trautman Date: 8 February 2010 10.1 Active Learning Review What questions should be

264 views • 4 slides
Active Learning: Rethinking Our Teaching to Promote Deeper Learning Facilitated by Ken Silvestri,

Active Learning: Rethinking Our Teaching to Promote Deeper Learning Facilitated by Ken Silvestri,

Active Learning: Rethinking Our Teaching to Promote Deeper Learning Facilitated by Ken Silvestri, CFE Instructional Designer Adapted for Institute of Technology By Menaka Abraham OVERVIEW Why Active Learning What is Active Learning

542 views • 18 slides
Active Learning for Regression: Active Learning for Regression: Algorithms and Applications

Active Learning for Regression: Active Learning for Regression: Algorithms and Applications

LAMDA group, Nanjing University Nov. 5, 2009. Active Learning for Regression: Active Learning for Regression: Algorithms and Applications Algorithms and Applications Masashi Sugiyama Tokyo Institute of Technology sugi@cs.titech.ac.jp

870 views • 64 slides
Toward Active Learning in Data Selection: Automatic Discovery of Language Features During

Toward Active Learning in Data Selection: Automatic Discovery of Language Features During

Toward Active Learning in Data Selection: Automatic Discovery of Language Features During Elicitation Jonathan Clark Robert Frederking Lori Levin Language Technologies Institute Carnegie Mellon University Pittsburgh, PA Feature Detection

550 views • 26 slides
Introduction to training offering by EMA Training Module PhV-M0 This module provides an overview

Introduction to training offering by EMA Training Module PhV-M0 This module provides an overview

Introduction to training offering by EMA Training Module PhV-M0 This module provides an overview of all training offerings planned by EMA in the area of EudraVigilance, EVDAS, ADR reporting and signal detection providing learning paths for new

343 views • 23 slides
Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds

Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds

Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds Sudheendra Vijayanarasimhan Kristen Grauman Department of Computer Science University of Texas at Austin Austin, Texas Introduction Problem Our

1.48k views • 80 slides
Training Neural Networks: Normalization, Regularization etc. Intro to Deep Learning, Fall 2020 1

Training Neural Networks: Normalization, Regularization etc. Intro to Deep Learning, Fall 2020 1

Training Neural Networks: Normalization, Regularization etc. Intro to Deep Learning, Fall 2020 1 Quick Recap: Training a network Divergence between desired output and Average over all actual output of net for a given input training instances

1.75k views • 140 slides
Using active learning pedagogy to enable the Presentation by Donna Whitehead teaching of

Using active learning pedagogy to enable the Presentation by Donna Whitehead teaching of

Using active learning pedagogy to enable the Presentation by Donna Whitehead teaching of enterprise and entrepreneurial skills Active learning Active learning methodology has become a preferred way to change the traditional teacher

146 views • 11 slides
Using R for Active Learning and Self-assessment in an e-Learning Environment Arnau Mir, Margaret

Using R for Active Learning and Self-assessment in an e-Learning Environment Arnau Mir, Margaret

Using R for Active Learning and Self-assessment in an e-Learning Environment Arnau Mir, Margaret Mir-Juli and Monica J. Ruiz-Mir University of the Balearic Islands Palma de Mallorca, SPAIN Using R for Active Learning and Self-assessment

740 views • 12 slides
Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo

Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo

Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo Institute of Technology Active Learning (NLP Motivation) NLP (common scenario) Large amounts of unlabeled data Large amounts of unlabeled

706 views • 36 slides
Chapter 15 User Support and On-Line Information Active Learning with Minimalist Manuals

Chapter 15 User Support and On-Line Information Active Learning with Minimalist Manuals

Chapter 15 User Support and On-Line Information Active Learning with Minimalist Manuals Minimalist instruction Removing many of the obstacles that make learning difficult The Training Wheels Word Processor Limits the learner to

452 views • 6 slides
Learning J.J. (Jia-Jie) Zhu Boston College GAAL 2 Active learning classify 400 instances 30

Learning J.J. (Jia-Jie) Zhu Boston College GAAL 2 Active learning classify 400 instances 30

Generative Adversarial Active Learning J.J. (Jia-Jie) Zhu Boston College GAAL 2 Active learning classify 400 instances 30 randomly selected 30 selected using AL using logistic regression 70% accuracy 90% accuracy pool-based active

801 views • 12 slides
Course outline Online decision making 1. Statistical active learning 2. Combinatorial

Course outline Online decision making 1. Statistical active learning 2. Combinatorial

Active Learning and Optimized Information Gathering Lecture 3 Reinforcement Learning CS 101.2 Andreas Krause Announcements Homework 1: out tomorrow Due Thu Jan 22 Project Proposal due Tue Jan 27 (start soon!) Office hours Come to

573 views • 23 slides

More recommend