1 / 24

What do you do when you know that you don’t know?

What do you do when you know that you don’t know?. Abhijit Bendale*, Terrance Boult Samsung Research America* University of Colorado of Colorado Springs. Facial Attributes.

aitana
Download Presentation

What do you do when you know that you don’t know?

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. What do you do when you know that you don’t know? Abhijit Bendale*, Terrance Boult Samsung Research America* University of Colorado of Colorado Springs

  2. Facial Attributes N Kumar, A Berg, P Belhumeur, S Nayar “Describable Visual Attributes for Face Verification and Image Search” IEEE TPAMI 2011 B Klare, S Klum, J Klontz, E Taborsky, T Akgul, A Jain “Suspect Identification Based on Descriptive Facial Attributes” IEEE/IAPR IJCB 2014

  3. Facial Attributes Based Face Recognition Probe Face Recognition System Gallery Mugshots CCTV B Klare, S Klum, J Klontz, E Taborsky, T Akgul, A Jain “Suspect Identification Based on Descriptive Facial Attributes” IEEE/IAPR IJCB 2014

  4. Unknowns in Real World N Kumar, A Berg, P Belhumeur, S Nayar “Describable Visual Attributes for Face Verification and Image Search” IEEE TPAMI 2011 M Wilber, E Rudd, B Heflin, Y Lui, T Boult “Exemplar codes for facial attributes and tattoo recognition” WACV 2014

  5. Handling Missing Features Reduced Feature Models Model 1 Model 2 Model 3 Model 4 …. Model 5 Y. Ding and A. Ross. “A comparison of imputation methods for handling missing scores in biometric fusion”. Pattern Recognition, pages 919–933, 2012 G. Chechik, G. Heitz, G. Elidan, P. Abbeel, and D. Koller. “Max-margin classification of data with absent features”. J. of Machine Learning Research, pages 1–21, 2008.

  6. Our Operational Scenario • Access to only stored model and operational data • No prior knowledge of nature of missing data • Storage limitation : Cannot store countless “reduced models” • Impractical for face recognition Operational Data / Support Vectors Stored Model Decision Score Test Data P(A) or P(B) Missing Data At Test Time

  7. Operational Adaptation

  8. Support Vector Machines subject to Differentiate wrt w and b to get solution

  9. SVM Bias Projection

  10. Missing Data in Context of Linear SVMs and Imputation X1 = 0 Misclassification caused due to zero imputation X2 = 0

  11. Run Time Bias Estimation New hyper plane obtained After optimizing the bias term • Project Operational Data • Optimize for Bias • Obtain optimal hyper plane in operational domain • Classify in the projected domain

  12. Run Time Bias Estimation Refactored Projection Error Refactor Risk Optimal Bias : Minimize Refactor Risk

  13. Bias vs Refactor Risk

  14. Experimental Setup USPS Dataset 0-9 Numbers, 9298 images, 7291 for training, 2007 for testing Each image represented as 256 dimensional vector Binary Classification : 1-vs-All MNIST Dataset 0-9 Numbers, 70000 images, 60000 for training, 10000 for testing Image size 28x28. Feature size 784 Binary Classification : 1-vs-All LFW Dataset Pair Matching 6000 images. 5400 Training, 600 Testing 10 fold validation Feature type: Attributes of faces. Feature vector size: 146 Binary Classification : Same pair, different Pair

  15. Comparison with Other Methods [5] G. Chechik, G. Heitz, G. Elidan, P. Abbeel, and D. Koller. “Max-margin classification of data with absent features”. J. of Machine Learning Research, pages 1–21, 2008. [11] Z. Ghahramani and M. I. Jordan. “Supervised learning from incomplete data via an EM approach” NIPS 1994 [29] A. J. Smola, S. V. N. Vishwanathan, and T. Hofmann. Kernel methods for missing variables. In Proc. Wksp on Articial Intelligence and Statistics, 2005

  16. USPS Dataset for Handwriting Recognition

  17. MNIST Dataset for Handwriting Recognition

  18. Facial Attributes on LFW dataset for Face Verification

  19. Risk Estimation for Missing Data Meta-Recognition False Accept Rate Meta-Recognition Miss Detection Rate

  20. Meta-Recognition Analysis for Missing Data Ideal Risk Estimator

  21. Conclusion • Operational Adaptation for Biometrics Systems • Algorithm for Run Time Bias Estimation for SVMs as an effective way for handling missing features • Adaptation Risk Estimator for SVMs • Meta-Recognition Analysis for handling missing features

  22. Future Work A Bendale, T Boult “Reliable Posterior Probability Estimation for Streaming Face Recognition” CVPR Biometrics Workshop 2014 A Bendale, T Boult “Towards Open World Recognition” CVPR 2015 A Bendale, T Boult “Towards Open Set Deep Networks” CVPR 2016 Tuesday – June 28 10:00 – 10:30 AM Short Oral 10:30 AM – 12:30 PM Poster Session

  23. We are releasing code for this work along with libsvm wrappers…! I don’t trust you or your claims  Awesome..!!

More Related