Machine learning & category recognition Cordelia Schmid Jakob Verbeek.

Slides:



Advertisements
Similar presentations
Clustering with k-means and mixture of Gaussian densities Jakob Verbeek December 3, 2010 Course website:
Advertisements

TP14 - Local features: detection and description Computer Vision, FCUP, 2014 Miguel Coimbra Slides by Prof. Kristen Grauman.
Object Recognition using Invariant Local Features Applications l Mobile robots, driver assistance l Cell phone location or object recognition l Panoramas,
CS4670 / 5670: Computer Vision Bag-of-words models Noah Snavely Object
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Global spatial layout: spatial pyramid matching Spatial weighting the features Beyond bags of features: Adding spatial information.
Image alignment Image from
Discriminative and generative methods for bags of features
Object Recognition with Invariant Features n Definition: Identify objects or scenes and determine their pose and model parameters n Applications l Industrial.
Effective Image Database Search via Dimensionality Reduction Anders Bjorholm Dahl and Henrik Aanæs IEEE Computer Society Conference on Computer Vision.
Robust and large-scale alignment Image from
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
1 Image Recognition - I. Global appearance patterns Slides by K. Grauman, B. Leibe.
Lecture 28: Bag-of-words models
Generic Object Recognition -- by Yatharth Saraf A Project on.
CS335 Principles of Multimedia Systems Content Based Media Retrieval Hao Jiang Computer Science Department Boston College Dec. 4, 2007.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Object Recognition: History and Overview Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and Jean Ponce.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Distinctive Image Feature from Scale-Invariant KeyPoints
Object Recognition: Conceptual Issues Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and K. Grauman.
Distinctive image features from scale-invariant keypoints. David G. Lowe, Int. Journal of Computer Vision, 60, 2 (2004), pp Presented by: Shalomi.
Object Class Recognition Using Discriminative Local Features Gyuri Dorko and Cordelia Schmid.
Visual Object Recognition Rob Fergus Courant Institute, New York University
1 Invariant Local Feature for Object Recognition Presented by Wyman 2/05/2006.
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Keypoint-based Recognition and Object Search
Object Recognition and Augmented Reality
Review: Intro to recognition Recognition tasks Machine learning approach: training, testing, generalization Example classifiers Nearest neighbor Linear.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Distinctive Image Features from Scale-Invariant Keypoints By David G. Lowe, University of British Columbia Presented by: Tim Havinga, Joël van Neerbos.
Unsupervised Learning of Categories from Sets of Partially Matching Image Features Kristen Grauman and Trevor Darrel CVPR 2006 Presented By Sovan Biswas.
Introduction to Machine Learning for Category Representation
Step 3: Classification Learn a decision rule (classifier) assigning bag-of-features representations of images to different classes Decision boundary Zebra.
Keypoint-based Recognition Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/04/10.
The EM algorithm, and Fisher vector image representation
COMP 875 Machine Learning Methods in Image Analysis.
Classification 2: discriminative models
Machine learning & category recognition Cordelia Schmid Jakob Verbeek.
Object Tracking/Recognition using Invariant Local Features Applications l Mobile robots, driver assistance l Cell phone location or object recognition.
Computer Vision CS 776 Spring 2014 Recognition Machine Learning Prof. Alex Berg.
Marcin Marszałek, Ivan Laptev, Cordelia Schmid Computer Vision and Pattern Recognition, CVPR Actions in Context.
Perceptual and Sensory Augmented Computing Visual Object Recognition Tutorial Visual Object Recognition Bastian Leibe & Computer Vision Laboratory ETH.
Lecture 4: Feature matching CS4670 / 5670: Computer Vision Noah Snavely.
Building local part models for category-level recognition C. Schmid, INRIA Grenoble Joint work with G. Dorko, S. Lazebnik, J. Ponce.
Bag-of-features models. Origin 1: Texture recognition Texture is characterized by the repetition of basic elements or textons For stochastic textures,
Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
Video Google: A Text Retrieval Approach to Object Matching in Videos Josef Sivic and Andrew Zisserman.
10/31/13 Object Recognition and Augmented Reality Computational Photography Derek Hoiem, University of Illinois Dali, Swans Reflecting Elephants.
Classification 1: generative and non-parameteric methods Jakob Verbeek January 7, 2011 Course website:
MSRI workshop, January 2005 Object Recognition Collected databases of objects on uniform background (no occlusions, no clutter) Mostly focus on viewpoint.
Evaluation of Research Theme CogB. Objectives LEAR: LEArning and Recognition in vision Visual recognition and scene understanding –Particular objects.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
Visual Categorization With Bags of Keypoints Original Authors: G. Csurka, C.R. Dance, L. Fan, J. Willamowski, C. Bray ECCV Workshop on Statistical Learning.
Local invariant features Cordelia Schmid INRIA, Grenoble.
Local invariant features Cordelia Schmid INRIA, Grenoble.
Methods for classification and image representation
CS 1699: Intro to Computer Vision Support Vector Machines Prof. Adriana Kovashka University of Pittsburgh October 29, 2015.
Lecture 08 27/12/2011 Shai Avidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
Local features: detection and description
Goggle Gist on the Google Phone A Content-based image retrieval system for the Google phone Manu Viswanathan Chin-Kai Chang Ji Hyun Moon.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Machine learning & object recognition Cordelia Schmid Jakob Verbeek.
Machine Learning and Category Representation Jakob Verbeek November 25, 2011 Course website:
Lecture 07 13/12/2011 Shai Avidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
Paper Presentation: Shape and Matching
By Suren Manvelyan, Crocodile (nile crocodile?) By Suren Manvelyan,
Object detection as supervised classification
SIFT keypoint detection
Presentation transcript:

Machine learning & category recognition Cordelia Schmid Jakob Verbeek

This class Part 1: Visual object recognition Part 2 : Machine learning

Visual recognition - Objectives Particular objects and scenes, large databases …

Finding the object despite possibly large changes in scale, viewpoint, lighting and partial occlusion  requires invariant description Viewpoint Scale Lighting Occlusion Difficulties

Very large images collection  need for efficient indexing –Flickr has 2 billion photographs, more than 1 million added daily –Facebook has 15 billion images (~27 million added daily) –Large personal collections –Video collections, i.e., YouTube

Search photos on the web for particular places Find these landmarks...in these images and 1M more Applications

Take a picture of a product or advertisement  find relevant information on the web [Pixee – Milpix]

Applications Finding stolen/missing objects in a large collection …

Applications Copy detection for images and videos Search in 200h of video Query video

10 K. Grauman, B. Leibe Sony Aibo – Robotics –Recognize docking station –Communicate with visual cards –Place recognition –Loop closure in SLAM Slide credit: David Lowe Applications

Instance-level recognition: Approach Extraction of invariant image descriptors Matching descriptors between images -Matching of the query images to all images of a database -Speed-up by efficient indexing structures Geometric verification –Verification of spatial consistency for a short list

This class Lecture 2: Local invariant features –Student presentation: scale and affine invariant interest point detectors

This class Lecture 3: Instance-level recognition: efficient search –Student presentation: scalable recognition with a vocabulary tree

Visual recognition - Objectives Object classes and categories (intra-class variability)

Image classification: assigning label to the image Tasks Car: present Cow: present Bike: not present Horse: not present … Object localization: define the location and the category Car Cow Location Category Visual object recognitionVisual recognition - Objectives

Difficulties: within object variations Variability : Camera position, Illumination,Internal parameters Within-object variations

Difficulties: within-class variations

Visual category recognition Robust image description –Appropriate descriptors for objects and categories Statistical modeling and machine learning for vision –Selection and adaptation of existing techniques

Why machine learning? Early approaches: simple features + handcrafted models Can handle only few images, simples tasks L. G. Roberts, Machine Perception of Three Dimensional Solids, Ph.D. thesis, MIT Department of Electrical Engineering, 1963.

Why machine learning? Early approaches: manual programming of rules Tedious, limited and does not take into accout the data Y. Ohta, T. Kanade, and T. Sakai, “An Analysis System for Scenes Containing objects with Substructures,” International Joint Conference on Pattern Recognition, 1978.

Why machine learning? Today lots of data, complex tasks Internet images, personal photo albums Movies, news, sports

Why machine learning? Today lots of data, complex tasks Surveillance and security Medical and scientific images

Why machine learning? Today: Lots of data, complex tasks Instead of trying to encode rules directly, learn them from examples of inputs and desired outputs

Types of learning problems Supervised –Classification –Regression Unsupervised Semi-supervised Reinforcement learning Active learning ….

Image classification : Approach Excellent results in the presence of background clutter bikesbooksbuildingcarspeoplephonestrees Bag-of-features for image classification

Classification SVM Extract regionsCompute descriptors Find clusters and frequencies Compute distance matrix

Spatial pyramids: perform matching in 2D image space This class Lecture 4: Bag-of-features models for image classification –Student presentation: beyond bags of features: spatial pyramids

Object category localization: examples Car Sofa Bicycle Horse

Object category localization Method with sliding windows (Each window is classified as containing or not the targeted object) Learn a classifier by providing positive and negative examples

Localization approach Histogram of oriented image gradients as image descriptor SVM as classifier, importance weighted descriptors

Localization of “shape” categories Window descriptor + SVMHorse localization

Localization based on shape

This class Lecutre 5: Category-level object localization –Student presentation: object detection with discriminatively trained part based models

This class - schedule Session 1, October –Cordelia Schmid: Introduction –Jakob Verbeek: Introduction Machine Learning Session 2, December –Jakob Verbeek: Clustering with k-means, mixture of Gaussians –Cordelia Schmid: Local invariant features –Student presentation 1 : Scale and affine invariant interest point detectors, Mikolajczyk and Schmid, IJCV Session 3, December –Cordelia Schmid: Instance-level recognition: efficient search –Student presentation 2: Scalable recognition with a vocabulary tree, Nister and Stewenisus, CVPR 2006.

Plan for the course Session 4, December –Jakob Verbeek: Mixture of Gaussians, EM algo.,Fisher Vector image representation –Cordelia Schmid: Bag-of-features models for category-level classification –Student presentation2: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories, Lazebnik, Schmid and Ponce, CVPR Session 5, January –Jakob Verbeek: Classification 1: generative and non-parameteric methods –Student presentation 4: Large-scale image retrieval with compressed Fisher vectors, Perronnin, Liu, Sanchez and Poirier, CVPR –Cordelia Schmid: Category level localization: Sliding window and shape model –Student presentation 5: Object detection with discriminatively trained part based methods, McAllester and Ramanan, PAMI This class - schedule

Plan for the course Session 6, January –Jakob Verbeek: Classification 2: discriminative models –Student presentation 6:TagProp: discriminative metric learning in nearest neighbor models for image auto-annotation, Guillaumin, Mensink, Verbeek and Schmid, ICCV –Student presentation 7: IMG2GPS: estimating geographic information from a single image, Hays and Efros, CVPR This class - schedule

This class Class web page at – –Slides available after class Student presentations –20 minutes oral presentation with slides, 5 minutes questions –Two students present together one paper Grades –50% final exam –25% presentation –25% short quiz after each presentation