nips nips2012 nips2012-344 nips2012-344-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Sergey Karayev, Tobias Baumgartner, Mario Fritz, Trevor Darrell
Abstract: In a large visual multi-class detection framework, the timeliness of results can be crucial. Our method for timely multi-class detection aims to give the best possible performance at any single point after a start time; it is terminated at a deadline time. Toward this goal, we formulate a dynamic, closed-loop policy that infers the contents of the image in order to decide which detector to deploy next. In contrast to previous work, our method significantly diverges from the predominant greedy strategies, and is able to learn to take actions with deferred values. We evaluate our method with a novel timeliness measure, computed as the area under an Average Precision vs. Time curve. Experiments are conducted on the PASCAL VOC object detection dataset. If execution is stopped when only half the detectors have been run, our method obtains 66% better AP than a random ordering, and 14% better performance than an intelligent baseline. On the timeliness measure, our method obtains at least 11% better performance. Our method is easily extensible, as it treats detectors and classifiers as black boxes and learns from execution traces using reinforcement learning. 1
[1] M Everingham, L Van Gool, C K I Williams, J Winn, and A Zisserman. The PASCAL VOC Challenge. http://www.pascal-network.org/challenges/VOC/, 2010. 2, 3, 6
[2] N Dalal and B Triggs. Histograms of Oriented Gradients for Human Detection. In CVPR, pages 886–893, 2005. 3
[3] David G Lowe. Distinctive Image Features from Scale-Invariant Keypoints. IJCV, 60(2):91–110, November 2004. 3
[4] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. PAMI, 32(9):1627–1645, September 2010. 3
[5] Andrea Vedaldi, Varun Gulshan, Manik Varma, and Andrew Zisserman. Multiple kernels for object detection. ICCV, pages 606–613, September 2009. 3
[6] Aude Oliva and Antonio Torralba. Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope. IJCV, 42(3):145–175, 2001. 3
[7] Antonio Torralba, Kevin P Murphy, and William T Freeman. Contextual Models for Object Detection Using Boosted Random Fields. MIT CSAIL Technical Report, 2004. 3
[8] Carolina Galleguillos and Serge Belongie. Context based object categorization: A critical survey. Computer Vision and Image Understanding, 114(6):712–722, June 2010. 3
[9] Santosh K Divvala, Derek Hoiem, James H Hays, Alexei A Efros, and Martial Hebert. An empirical study of context in object detection. In CVPR, pages 1271–1278, June 2009. 3
[10] Paul Viola and Michael Jones. Rapid object detection using a boosted cascade of simple features. In CVPR, 2001. 3, 4
[11] Minmin Chen, Zhixiang (Eddie) Xu, Kilian Q Weinberger, Olivier Chapelle, and Dor Kedem. Classifier Cascade for Minimizing Feature Evaluation Cost. In AISTATS, 2012. 3
[12] Sudheendra Vijayanarasimhan and Ashish Kapoor. Visual Recognition and Detection Under Bounded Computational Resources. In CVPR, pages 1006–1013, 2010. 3
[13] Tianshi Gao and Daphne Koller. Active Classification based on Value of Classifier. In NIPS, 2011. 3
[14] Shipeng Yu, Balaji Krishnapuram, Romer Rosales, and R Bharat Rao. Active Sensing. In AISTATS, pages 639–646, 2009. 3
[15] Richard S Sutton and Andrew G Barto. Reinforcement Learning: An Introduction. MIT Press, 1998. 4, 5
[16] Nicholas Roy and Geoffrey Gordon. Exponential Family PCA for Belief Compression in POMDPs. In NIPS, 2002. 5
[17] Cody Kwok and Dieter Fox. Reinforcement Learning for Sensing Strategies. In IROS, 2004. 5
[18] Su-In Lee, Varun Ganapathi, and Daphne Koller. Efficient Structure Learning of Markov Networks using L1-Regularization. In NIPS, 2006. 6
[19] Ariel Jaimovich and Ian Mcgraw. FastInf: An Efficient Approximate Inference Library. Journal of Machine Learning Research, 11:1733–1736, 2010. 6
[20] Chaitanya Desai, Deva Ramanan, and Charless Fowlkes. Discriminative models for multi-class object layout. In ICCV, pages 229–236, September 2009. 6
[21] Pedro F Felzenszwalb, Ross B Girshick, and David McAllester. Cascade object detection with deformable part models. In CVPR, pages 2241–2248. IEEE, June 2010. 7 9