Roles of local and global information in image classification Devi Parikh.

Slides:



Advertisements
Similar presentations
Grammar By S.T: Hatoof Ali Ababneh. 7th Question 1 ………. are tall. They C. It B. The D. There.
Advertisements

Attributes for Classifier Feedback Amar Parkash and Devi Parikh.
7 Diplomacy. What is Diplomacy? Why is Diplomacy Necessary?
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
My name is Dustin Boswell and I will be presenting: Ensemble Methods in Machine Learning by Thomas G. Dietterich Oregon State University, Corvallis, Oregon.
Simultaneous Image Classification and Annotation Chong Wang, David Blei, Li Fei-Fei Computer Science Department Princeton University Published in CVPR.
Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs Roozbeh Mottaghi 1, Sanja Fidler 2, Jian Yao 2, Raquel Urtasun 2, Devi Parikh 3 1 UCLA.
Discriminative and generative methods for bags of features
Multiple Criteria for Evaluating Land Cover Classification Algorithms Summary of a paper by R.S. DeFries and Jonathan Cheung-Wai Chan April, 2000 Remote.
Beyond bags of features: Part-based models Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Relative Attributes Presenter: Shuai Zheng (Kyle) Supervised by Philip H.S. Torr Author: Devi Parikh (TTI-Chicago) and Kristen Grauman (UT-Austin)
Ensemble Learning: An Introduction
Pedestrian Recognition Machine Perception and Modeling of Human Behavior Manfred Lau.
Artificial Neural Networks
An interactive vocabulary game Government Sydney, Zach, Mason, Shanilyn, Max, and Chance.
A Generic Approach for Image Classification Based on Decision Tree Ensembles and Local Sub-windows Raphaël Marée, Pierre Geurts, Justus Piater, Louis Wehenkel.
Cultural Visual Literacy Images Americans Should Recognize.
MEASURING AND ASSESSING FINANCIAL CAPABILITY: PRACTITIONERS SHARE STUDIES AND FINDINGS.
Unsupervised Learning of Hierarchical Spatial Structures Devi Parikh, Larry Zitnick and Tsuhan Chen.
Step 3: Classification Learn a decision rule (classifier) assigning bag-of-features representations of images to different classes Decision boundary Zebra.
Sampling: The Hows and Whys Driven to Discover Enabling Student Inquiry through Citizen Science Driven to Discover Enabling Student Inquiry through Citizen.
ENSEMBLE LEARNING David Kauchak CS451 – Fall 2013.
Machine Learning Chapter 4. Artificial Neural Networks
Images for our Map Toolkit
The Role of Features, Algorithms and Data in Visual Recognition Reporter: WuBin Data:
Classifiers Given a feature representation for images, how do we learn a model for distinguishing features from different classes? Zebra Non-zebra Decision.
1 Pattern Recognition Pattern recognition is: 1. A research area in which patterns in data are found, recognized, discovered, …whatever. 2. A catchall.
Whiteboard Shape Recognition using Deformable Templates and Loopy Belief Propogation Noah Snavely David Bargeron April 2004.
 1 HR-XML Consortium, Inc..  2 The HR Industry.
Chapter 4: Pattern Recognition. Classification is a process that assigns a label to an object according to some representation of the object’s properties.
Copyright © 2009 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 7 MEASURING PRODUCTIVITY.
Human pose recognition from depth image MS Research Cambridge.
Presenting by Sara Gholami.  Iran formerly known as Persia, is one of the world’s oldest continuous major civilizations. Iran has great tourist attractions.
WhittleSearch: Image Search with Relative Attribute Feedback CVPR 2012 Adriana Kovashka Devi Parikh Kristen Grauman University of Texas at Austin Toyota.
© Devi Parikh 2008 Devi Parikh and Tsuhan Chen Carnegie Mellon University April 3, ICASSP 2008 Bringing Diverse Classifiers to Common Grounds: dtransform.
Hough Transform Procedure to find a shape in an image Shape can be described in parametric form Shapes in image correspond to a family of parametric solutions.
Terms to know by the end of the unit: Image obtained from:
1- What is the role of international organizations to address the data management requirements? To facilitate and promote the management of data at the.
COMP24111: Machine Learning Ensemble Models Gavin Brown
BABCOCK MEDICAL SOCIETY: OUR VISION AND GOALS. Introduction  Inaugurated in June 2015  The Babcock Medical Society (BMS) was instituted to act as an.
Combining multiple learners Usman Roshan. Decision tree From Alpaydin, 2010.
Observation vs. Inferences The Local Environment.
Sampling Technique: Muncie Capture-recapture By Soumaly P. Bounket Ben Freed Tom Lockhart.
Introduction to Business Chapter 3 Economic Roles Essential Question: What is our role in the economy?
A PPLICATIONS OF TOPIC MODELS Daphna Weinshall B Slides credit: Joseph Sivic, Li Fei-Fei, Brian Russel and others.
Touch Master Is my child ready for math at school? School Readiness Evaluation.
Image from
Why spend a day at an AMC Theater?. Hundreds of movies  Watch any movie at any time  Movies available in Dine-in, Imax, AMC Independent, sensory friendly,
Machine Learning Usman Roshan Dept. of Computer Science NJIT.
Global localization of 3D anatomical structures by pre-filtered Hough Forests and discrete optimization Speaker: Longwei Fang Date: 8/July,2016.
Short or Tall?. Short Tall Short Tall Short Tall. 3
Machine Learning: Ensemble Methods
What we do to think geographically:
MIRA, SVM, k-NN Lirong Xia. MIRA, SVM, k-NN Lirong Xia.
Trees, bagging, boosting, and stacking
Recognizing Deformable Shapes
Image Recognition. Contents: Motivation Objective Definition Introduction Preprocessing / Edge Detection Neural Networks in Image Recognition Practical.
ASSIGNMENT NO.-2.
Product Service Planning Skills
Location Prediction and Spatial Data Mining (S. Shekhar)
Inferences On Two Samples
Boosting Nearest-Neighbor Classifier for Character Recognition
Apollo Weize Sun Feb.17th, 2017.
FEBRUARY 28, 2018 OBJECTIVE – Students will learn the difference between climate change and global warming. Students will investigate causes of climate.
Human Speech Perception and Feature Extraction
MEASURING PRODUCTIVITY
Drawing Conclusions & Making Generalizations and Inferences
Adversarial Machine Learning in Image Recognition
[Sequence -> Part 1 Process Plan]
MIRA, SVM, k-NN Lirong Xia. MIRA, SVM, k-NN Lirong Xia.
Presentation transcript:

Roles of local and global information in image classification Devi Parikh

Coast HighwayMountain Street Forest Inside cityOpen country Tall buildings BathroomBedroomDining roomGym KitchenLiving roomMovie theater Stair case Aeroplane Car-rearFace Ketch Motorbike Watch OSR ISR CAL 2

Jumbled Images 3

Human Study: Intact Images

Human Study: Jumbled Images

Human Recognition of Jumbled Images Accuracy 6

How do we recognize them? Majority Vote of Local Independent Decisions? MRF Inference? … Are existing machine implementations of this model good enough? 7

Human Studies: Individual Blocks 8

Human Recognition of Individual Blocks Accuracy 9

Machine Experiments Assign blocks to codewords Accumulate p(scene|codewords) Pick class with highest votes

Majority Vote Results Proportion of matched responses 11

Classification of Jumbled Images Accuracy Need advanced modeling of global information 12

Feedback: Privacy Policy Feedback
Do Not Sell My Personal Information
About project: SlidePlayer Terms of Service

© 2024 SlidePlayer.com Inc. All rights reserved.