Sparselet Models for Efficient Multiclass Object Detection

Slides:



Advertisements
Similar presentations
Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
Advertisements

SE263 Video Analytics Course Project Initial Report Presented by M. Aravind Krishnan, SERC, IISc X. Mei and H. Ling, ICCV’09.
Data Mining Feature Selection. Data reduction: Obtain a reduced representation of the data set that is much smaller in volume but yet produces the same.
Multi-Label Prediction via Compressed Sensing By Daniel Hsu, Sham M. Kakade, John Langford, Tong Zhang (NIPS 2009) Presented by: Lingbo Li ECE, Duke University.
Pattern Recognition and Machine Learning: Kernel Methods.
Computer vision: models, learning and inference Chapter 13 Image preprocessing and feature extraction.
Face Alignment with Part-Based Modeling
Submodular Dictionary Selection for Sparse Representation Volkan Cevher Laboratory for Information and Inference Systems - LIONS.
Many slides based on P. FelzenszwalbP. Felzenszwalb General object detection with deformable part-based models.
Computer vision: models, learning and inference
|| Dmitry Laptev, Joachim M. Buhmann Machine Learning Lab, ETH Zurich 05/09/14Dmitry Laptev1 Convolutional Decision Trees.
Face Recognition & Biometric Systems Support Vector Machines (part 2)
Extensions of wavelets
Ilias Theodorakopoulos PhD Candidate
Mean transform, a tutorial KH Wong mean transform v.5a1.
An Introduction to Sparse Coding, Sparse Sensing, and Optimization Speaker: Wei-Lun Chao Date: Nov. 23, 2011 DISP Lab, Graduate Institute of Communication.
Large-Scale, Real-World Face Recognition in Movie Trailers Week 2-3 Alan Wright (Facial Recog. pictures taken from Enrique Gortez)
Empowering visual categorization with the GPU Present by 陳群元 我是強壯 !
Learning Convolutional Feature Hierarchies for Visual Recognition
More sliding window detection: Discriminative part-based models Many slides based on P. FelzenszwalbP. Felzenszwalb.
Entropy-constrained overcomplete-based coding of natural images André F. de Araujo, Maryam Daneshi, Ryan Peng Stanford University.
Sparse and Overcomplete Data Representation
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
Chapter 7 Wavelets and Multi-resolution Processing.
Multi-Class Object Recognition Using Shared SIFT Features
Image Denoising with K-SVD Priyam Chatterjee EE 264 – Image Processing & Reconstruction Instructor : Prof. Peyman Milanfar Spring 2007.
Object Recognizing We will discuss: Features Classifiers Example ‘winning’ system.
The Implicit Mapping into Feature Space. In order to learn non-linear relations with a linear machine, we need to select a set of non- linear features.
6.829 Computer Networks1 Compressed Sensing for Loss-Tolerant Audio Transport Clay, Elena, Hui.
Multiscale transforms : wavelets, ridgelets, curvelets, etc.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
Generic object detection with deformable part-based models
Linear Algebra and Image Processing
CIVS, Statistics Dept. UCLA Deformable Template as Active Basis Zhangzhang Si UCLA Department of Statistics Ying Nian Wu, Zhangzhang Si, Chuck.
Jinhui Tang †, Shuicheng Yan †, Richang Hong †, Guo-Jun Qi ‡, Tat-Seng Chua † † National University of Singapore ‡ University of Illinois at Urbana-Champaign.
Multiclass object recognition
Game Theory Meets Compressed Sensing
TEMPLATE BASED SHAPE DESCRIPTOR Raif Rustamov Department of Mathematics and Computer Science Drew University, Madison, NJ, USA.
Cs: compressed sensing
Implementing a Speech Recognition System on a GPU using CUDA
Matrix Sparsification. Problem Statement Reduce the number of 1s in a matrix.
 Karthik Gurumoorthy  Ajit Rajwade  Arunava Banerjee  Anand Rangarajan Department of CISE University of Florida 1.
Deformable Part Models (DPM) Felzenswalb, Girshick, McAllester & Ramanan (2010) Slides drawn from a tutorial By R. Girshick AP 12% 27% 36% 45% 49% 2005.
Locality-constrained Linear Coding for Image Classification
Implementation and Optimization of SIFT on a OpenCL GPU Final Project 5/5/2010 Guy-Richard Kayombya.
Matrix Factorization & Singular Value Decomposition Bamshad Mobasher DePaul University Bamshad Mobasher DePaul University.
PRACTICAL TIME BUNDLE ADJUSTMENT FOR 3D RECONSTRUCTION ON THE GPU Siddharth Choudhary ( IIIT Hyderabad ), Shubham Gupta ( IIIT Hyderabad ), P J Narayanan.
1 Bilinear Classifiers for Visual Recognition Computational Vision Lab. University of California Irvine To be presented in NIPS 2009 Hamed Pirsiavash Deva.
Let W be a subspace of R n, y any vector in R n, and the orthogonal projection of y onto W. …
Date of download: 7/7/2016 Copyright © 2016 SPIE. All rights reserved. Evaluation of the orthogonal matching pursuit (OMP) cost over the target space in.
Non-separable SVM's, and non-linear classification using kernels Jakob Verbeek December 16, 2011 Course website:
Parallel Image Processing: Active Contour Algorithm
Dimensionality Reduction and Principle Components Analysis
Object detection with deformable part-based models
CLASSIFICATION OF TUMOR HISTOPATHOLOGY VIA SPARSE FEATURE LEARNING Nandita M. Nayak1, Hang Chang1, Alexander Borowsky2, Paul Spellman3 and Bahram Parvin1.
LINEAR TRANSFORMATIONS
Presenter: Hajar Emami
Viewing Rectangle Coordinates (VRC)
C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs Shuo Wang1, Zhe Li2, Caiwen Ding2, Bo Yuan3, Qinru Qiu2, Yanzhi Wang2,
Basic Algorithms Christina Gallner
Singular Value Decomposition
Mean transform , a tutorial
Outline S. C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo”, IEEE Transactions On Pattern Analysis And Machine.
STUDY AND IMPLEMENTATION
Parallelization of Sparse Coding & Dictionary Learning
Linear Algebra Lecture 40.
REU Week 3: Real-Time Video Anomaly Detection
Outline Sparse Reconstruction RIP Condition
Progress Report Alvaro Velasquez.
Image restoration, noise models, detection, deconvolution
Presentation transcript:

Sparselet Models for Efficient Multiclass Object Detection Present by Guilin Liu masc.cs.gmu.edu

Key Idea Use sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. Reconstruction of original part filter responses via sparse matrix-vector product GPU implementation masc.cs.gmu.edu

Problem/motivation Individual model become redundant as the number of categories grow------Sparse Coding Learn basis parts so reconstructing the response of a target model is efficient masc.cs.gmu.edu

Overview System pipeline masc.cs.gmu.edu

Overview masc.cs.gmu.edu

1. Sparse reconstruction Find a generic dictionary approximate the part filters pooled from a set of training models, subject to a sparsity constraint masc.cs.gmu.edu

1. Sparse reconstruction Solve the optimization problem busing the Orthogonal Matching Pursuit algorithm(OMP) Two steps: Fixed D, optimize α Fixex α, optimize D masc.cs.gmu.edu

2. Precomputation & efficient reconstruction masc.cs.gmu.edu

2. Precomputation & efficient reconstruction Precompute convolutions for all sparselets Approximate t convolution response by linear combination of the activation vectors from step 1. masc.cs.gmu.edu

3. Implementation(CPU, GPU) The independence and parallelizablity of: Convolution, HOG computation and distance transforms CPU implementation: CPU cach miss limited the overall speedup GPU implementation: Compute image pyramids and HOG features Compute filter responses to root, part or part basis filter masc.cs.gmu.edu

4. Experiments Reconstruction error masc.cs.gmu.edu

4. Experiments 2. held-out evaluation masc.cs.gmu.edu

4. Experiments 3. Average precision masc.cs.gmu.edu

masc.cs.gmu.edu