MIT CSAIL Vision interfaces Towards efficient matching with random hashing methods… Kristen Grauman Gregory Shakhnarovich Trevor Darrell.

Slides:



Advertisements
Similar presentations
Song Intersection by Approximate Nearest Neighbours Michael Casey, Goldsmiths Malcolm Slaney, Yahoo! Inc.
Advertisements

Object Recognition Using Locality-Sensitive Hashing of Shape Contexts Andrea Frome, Jitendra Malik Presented by Ilias Apostolopoulos.
Aggregating local image descriptors into compact codes
Nearest Neighbor Search in High Dimensions Seminar in Algorithms and Geometry Mica Arie-Nachimson and Daniel Glasner April 2009.
Algorithmic High-Dimensional Geometry 1 Alex Andoni (Microsoft Research SVC)
Overcoming the L 1 Non- Embeddability Barrier Robert Krauthgamer (Weizmann Institute) Joint work with Alexandr Andoni and Piotr Indyk (MIT)
Big Data Lecture 6: Locality Sensitive Hashing (LSH)
Searching on Multi-Dimensional Data
Efficiently searching for similar images (Kristen Grauman)
MIT CSAIL Vision interfaces Approximate Correspondences in High Dimensions Kristen Grauman* Trevor Darrell MIT CSAIL (*) UT Austin…
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features Kristen Grauman Trevor Darrell MIT.
Similarity Search in High Dimensions via Hashing
Database-Based Hand Pose Estimation CSE 6367 – Computer Vision Vassilis Athitsos University of Texas at Arlington.
Data Structures and Functional Programming Algorithms for Big Data Ramin Zabih Cornell University Fall 2012.
Fast High-Dimensional Feature Matching for Object Recognition David Lowe Computer Science Department University of British Columbia.
Effective Image Database Search via Dimensionality Reduction Anders Bjorholm Dahl and Henrik Aanæs IEEE Computer Society Conference on Computer Vision.
Small Codes and Large Image Databases for Recognition CVPR 2008 Antonio Torralba, MIT Rob Fergus, NYU Yair Weiss, Hebrew University.
Image classification Given the bag-of-features representations of images from different classes, how do we learn a model for distinguishing them?
Fast and Compact Retrieval Methods in Computer Vision Part II A. Torralba, R. Fergus and Y. Weiss. Small Codes and Large Image Databases for Recognition.
1 Jun Wang, 2 Sanjiv Kumar, and 1 Shih-Fu Chang 1 Columbia University, New York, USA 2 Google Research, New York, USA Sequential Projection Learning for.
Similarity Search in High Dimensions via Hashing Aristides Gionis, Protr Indyk and Rajeev Motwani Department of Computer Science Stanford University presented.
1 An Empirical Study on Large-Scale Content-Based Image Retrieval Group Meeting Presented by Wyman
Nearest Neighbor Retrieval Using Distance-Based Hashing Michalis Potamias and Panagiotis Papapetrou supervised by Prof George Kollios A method is proposed.
Y. Weiss (Hebrew U.) A. Torralba (MIT) Rob Fergus (NYU)
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2006 with a lot of slides stolen from Steve Seitz and.
Optimal Data-Dependent Hashing for Approximate Near Neighbors
J Cheng et al,. CVPR14 Hyunchul Yang( 양현철 )
Approximate Nearest Subspace Search with applications to pattern recognition Ronen Basri Tal Hassner Lihi Zelnik-Manor Weizmann Institute Caltech.
Agenda Introduction Bag-of-words models Visual words with spatial location Part-based models Discriminative methods Segmentation and recognition Recognition-based.
Large Scale Recognition and Retrieval. What does the world look like? High level image statistics Object Recognition for large-scale search Focus on scaling.
Efficient Image Search and Retrieval using Compact Binary Codes
Indexing Techniques Mei-Chen Yeh.
Efficient Algorithms for Matching Pedro Felzenszwalb Trevor Darrell Yann LeCun Alex Berg.
Image Based Positioning System Ankit Gupta Rahul Garg Ryan Kaminsky.
Unsupervised Learning of Categories from Sets of Partially Matching Image Features Kristen Grauman and Trevor Darrel CVPR 2006 Presented By Sovan Biswas.
Nearest Neighbor Paul Hsiung March 16, Quick Review of NN Set of points P Query point q Distance metric d Find p in P such that d(p,q) < d(p’,q)
Fast Similarity Search for Learned Metrics Prateek Jain, Brian Kulis, and Kristen Grauman Department of Computer Sciences University of Texas at Austin.
Minimal Loss Hashing for Compact Binary Codes
Classifiers Given a feature representation for images, how do we learn a model for distinguishing features from different classes? Zebra Non-zebra Decision.
IEEE Int'l Symposium on Signal Processing and its Applications 1 An Unsupervised Learning Approach to Content-Based Image Retrieval Yixin Chen & James.
Click to edit Master subtitle style 2/23/10 Time and Space Optimization of Document Content Classifiers Dawei Yin, Henry S. Baird, and Chang An Computer.
Sketching and Nearest Neighbor Search (2) Alex Andoni (Columbia University) MADALGO Summer School on Streaming Algorithms 2015.
Similarity Searching in High Dimensions via Hashing Paper by: Aristides Gionis, Poitr Indyk, Rajeev Motwani.
CVPR 2006 New York City Spatial Random Partition for Common Visual Pattern Discovery Junsong Yuan and Ying Wu EECS Dept. Northwestern Univ.
Query Sensitive Embeddings Vassilis Athitsos, Marios Hadjieleftheriou, George Kollios, Stan Sclaroff.
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
P ROBING THE L OCAL -F EATURE S PACE OF I NTEREST P OINTS Wei-Ting Lee, Hwann-Tzong Chen Department of Computer Science National Tsing Hua University,
A feature-based kernel for object classification P. Moreels - J-Y Bouguet Intel.
CS 1699: Intro to Computer Vision Support Vector Machines Prof. Adriana Kovashka University of Pittsburgh October 29, 2015.
Approximate Nearest Neighbors: Towards Removing the Curse of Dimensionality Piotr Indyk, Rajeev Motwani The 30 th annual ACM symposium on theory of computing.
Multi-object Similarity Query Evaluation Michal Batko.
Lecture 5: Statistical Methods for Classification CAP 5415: Computer Vision Fall 2006.
Optimal Data-Dependent Hashing for Nearest Neighbor Search Alex Andoni (Columbia University) Joint work with: Ilya Razenshteyn.
Lecture 26 Hand Pose Estimation Using a Database of Hand Images
Sublinear Algorithmic Tools 3
Object detection as supervised classification
Lecture 11: Nearest Neighbor Search
Approximate Correspondences in High Dimensions
Near(est) Neighbor in High Dimensions
Rob Fergus Computer Vision
Lecture 16: Earth-Mover Distance
Locality Sensitive Hashing
COSC 4335: Other Classification Techniques
Nearest Neighbors CSC 576: Data Mining.
CS5112: Algorithms and Data Structures for Applications
Data Mining Classification: Alternative Techniques
Lecture 15: Least Square Regression Metric Embeddings
Minwise Hashing and Efficient Search
President’s Day Lecture: Advanced Nearest Neighbor Search
Ronen Basri Tal Hassner Lihi Zelnik-Manor Weizmann Institute Caltech
Presentation transcript:

MIT CSAIL Vision interfaces Towards efficient matching with random hashing methods… Kristen Grauman Gregory Shakhnarovich Trevor Darrell

MIT CSAIL Vision interfaces Motivation: Content-based image retrieval Data set of 30 scenes in Boston 1,079 database images 89 query images Features: Harris-Affine detector (max m=3,595) MSER detector (max m=1,707) SIFT-PCA descriptors Query

MIT CSAIL Vision interfaces Content-based image retrieval Pyramid match: ~1 second / query Optimal match: ~2 hours / query Number top retrievals Accuracy Even this is far too slow for any web-scale application!

MIT CSAIL Vision interfaces Sub-linear time image search N << N h Randomized hashing techniques useful for sub-linear query time of very large image databases N Linear scan

MIT CSAIL Vision interfaces Pyramid match hashing For fixed-size sets, Locality-Sensitive Hashing [Indyk & Motwani 1998] provides bounded approximate similarity search over bijective matching [Indyk & Thaper 2003]; [Grauman & Darrell CVPR 2004, 2005] For varying set sizes, embedding of pyramid match (with product normalization) makes random hyperplane hashing possible under set intersection hash family of [Charikar 2002]. [Grauman PhD 2006]

MIT CSAIL Vision interfaces

MIT CSAIL Vision interfaces

MIT CSAIL Vision interfaces

MIT CSAIL Vision interfaces

MIT CSAIL Vision interfaces Single Frame Pose Estimation via Approximate Nearest Neighbor regression Obtain large DB of pose-appearance mappings Exploit fast methods for approximate nearest neighbor search in high dim. spaces. (e.g., LSH [Indyk and Motwani ‘98-’00]. )

MIT CSAIL Vision interfaces Approximate nearest neighbor techniques … … … Rendered (& hashed) Pose DB input Hash fcns. similar examples fall into same bucket in one or more hash table

MIT CSAIL Vision interfaces Single Frame Pose Estimation via Approximate Nearest Neighbor regression Render large DB of pose-appearance mappings Exploit fast methods for approximate nearest neighbor search in high dim. spaces. (e.g., LSH [Indyk and Motwani ‘98-’00]. ) Problem: signal distance dominated by nuisance variables Idea: find embedding (i.e., hash functions for LSH) most relevant to parameter (pose) similarity… [Shakhnarovich et. al ’03, Shakhnarovich ‘05]

MIT CSAIL Vision interfaces Pose estimation and Similarity-sensitive hashing … … … Rendered (& hashed) Pose DB input Pose- sensitive Hash fcns. NN similar in pose, not image [Shakhnarovich et. al ’03, Shakhnarovich ‘05]

MIT CSAIL Vision interfaces SSE / BoostPro Similarity Sensitive Embedding - Compute embedding H: I  {0, 1} N such that | H(I(  1 )) - H(I(  2 )) | is small if  1 is close to  2 | H(I(  1 )) - H(I(  2 )) | is large otherwise - Use the embedding with approximate nearest neighbors retrieval (LSH) - Find H by training boosted classifier to learn “same-pair” and concatenate resulting weak learners … [Shakhnarovich 2005]

MIT CSAIL Vision interfaces PSH results ~200,000 examples in DB; 2 sec [Shakhnarovich et al. 2003, 2005]

MIT CSAIL Vision interfaces Conclusions Random Hashing techniques allow broad search; well suited for very high dimensional spaces Useful in domains where there is no prior knowledge about how to cluster or model data… Similarity (parameter) sensitive hashing can find distance related to task…effectively learn problem dependent distance measure and efficient means to index.