Presentation on theme: "Ke Chen 1, Shaogang Gong 1, Tao Xiang 1, Chen Change Loy 2 1. Queen Mary, University of London 2. The Chinese University of Hong Kong VGG reading group."— Presentation transcript:
Ke Chen 1, Shaogang Gong 1, Tao Xiang 1, Chen Change Loy 2 1. Queen Mary, University of London 2. The Chinese University of Hong Kong VGG reading group presentation by Minh Hoai Cumulative Attribute Space for Age and Crowd Density Estimation
Tasks How old are they? How many people? What is the head angle?
A Regression Framework Input images AAM feature Segment feature Edge feature Texture feature Feature extraction FeaturesLabel space Label (age, count) Learn the mapping Regression
Data distribution of FG-NET Dataset Challenge – Sparse and Unbalanced data
Data distribution of UCSD Dataset Challenge – Sparse and Unbalanced data
Proposed Approach Solution: Attribute Learning can address data sparsity problem -- Exploits the shared characteristics between classes Has sematic meaning Question to address: How to exploit cumulative dependent nature of labels in regression? …… …… …… Age 20 Age 21 Age 60
Cumulative Attribute Age … 20 0 … 0 the rest Cumulative attribute (dependent) Vs. 0 1 … 20th 0 … 0 Non-cumulative attribute (independent) 0 0
Limitation of Non-cumulative Attribute Age … 20th 0 … 0 Age 60 60th 0 … … 0 … 0 0 … st 0 1 … 0 … Age 21
Advantages of Cumulative Attribute Age … 20 0 … 0 the rest Age … 60 0 … … 1 … 1 attribute changes 1 1 … 21 0 … attributes change
Proposed Framework xixi xixi Feature vector (e.g., intensity) yiyi yiyi Label (e.g., age) … aiai aiai Cumulative attribute yiyi 1 2 Our task Regressor How are these regressors learned? Can use any regression method: Support Vector Regression, Ridge Regression See next slide!
Regressor for Cumulative Attributes RegularizationRegression error # of training data Cumulative attribute Image feature vector Parameters to learn Closed-form solution:
Baseline Methods and Name Abbreviation xixi xixi Feature vector yiyi yiyi Label Cumulative attributes Non-Cumulative attributes Support Vector Regression (SVR) SVR CA-SVR NCA-SVR … … y i … …
Cumulative (CA) vs. Non-cumulative (NCA) Age Estimation Mean absolute error (lower is better) Percentage of prediction within 5 years (higher is better)
Cumulative (CA) vs. Non-cumulative (NCA) Crowd Counting Mean absolute error (lower is better) Mean squared error (lower is better) Mean deviation error (lower is better)
Crowd Counting Results CA-RR: our method; LSSVR: Suykens et al, IJCNN, 2001; KRR: An et al, CVPR, 2007; RFR: Liaw et al, R News, 2002; GPR: Chan et al, CVPR, 2008; RR: Chen et al, BMVC, 2012; Based on regression Proposed method, RR: Ridge Regression Ridge Regression without attributes
Age Estimation Results CA-SVR: our method; AGES: Geng et al, TPAMI, 2007; RUN: Yan et al, ICCV, 2007; Ranking: Yan et al, ICME, 2007; RED-SVM: Chang et al, ICPR, 2010; LARR: Guo et al, TIP, 2008; MTWGP: Zhang et al, CVPR, 2010; OHRank: Chang et al, CVPR, 2011; SVR: Guo et al, TIP, 2008; Proposed method, SVR: Support Vector Regression Not based on regression What is OHRank?
OHRank - Ordinal Hyperplanes Ranker SVM score for older than k Delta 0/1 function This is 10 4 slower than closed-form solution of regression
Robustness Against Sparse and Unbalanced Data Age Estimation Crowd Counting (Effects of removing random/certain label groups)
Feature Selection by Attributes Shape plays a more important role than texture for younger ages.
Summary Has a simple and neat idea Exploits cumulative dependent nature of label space Addresses sparse and unbalanced data problem