NDLI: Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection

Content Provider	IEEE Xplore Digital Library
Author	Tianfu Wu Song-Chun Zhu
Copyright Year	2013
Description	Author affiliation: Dept. of Stat., Univ. of California, Los Angeles, Los Angeles, CA, USA (Tianfu Wu; Song-Chun Zhu)
Abstract	Many object detectors, such as AdaBoost, SVM and deformable part-based models (DPM), compute additive scoring functions at a large number of windows scanned over image pyramid, thus computational efficiency is an important consideration beside accuracy performance. In this paper, we present a framework of learning cost-sensitive decision policy which is a sequence of two-sided thresholds to execute early rejection or early acceptance based on the accumulative scores at each step. A decision policy is said to be optimal if it minimizes an empirical global risk function that sums over the loss of false negatives (FN) and false positives (FP), and the cost of computation. While the risk function is very complex due to high-order connections among the two-sided thresholds, we find its upper bound can be optimized by dynamic programming (DP) efficiently and thus say the learned policy is near-optimal. Given the loss of FN and FP and the cost in three numbers, our method can produce a policy on-the-fly for Adaboost, SVM and DPM. In experiments, we show that our decision policy outperforms state-of-the-art cascade methods significantly in terms of speed with similar accuracy performance.
Sponsorship	IEEE Comput. Soc.
Starting Page	753
Ending Page	760
File Size	756488
Page Count	8
File Format	PDF
ISBN	9781479928408
ISSN	15505499
DOI	10.1109/ICCV.2013.98
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-12-01
Publisher Place	Australia
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Trajectory Upper bound Support vector machines Detectors Additives Histograms Object Detection Decision Policy Cost-Sensitive Computing Risk Minimization Dynamic Programming
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Weakly supervised object detector learning with model drift detection

FOR REVIEW: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection

Histograms of oriented gradients for human detection

Weakly supervised object detection with convex clustering

Efficient activity detection with max-subgraph search

Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection

An HOG-LBP human detector with partial occlusion handling

Feature seeding for action recognition

Learning near-optimal cost-sensitive decision policy for object detection.

Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection

Similar Documents

Weakly supervised object detector learning with model drift detection

FOR REVIEW: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection

Histograms of oriented gradients for human detection

Weakly supervised object detection with convex clustering

Efficient activity detection with max-subgraph search

Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection

An HOG-LBP human detector with partial occlusion handling

Feature seeding for action recognition

Learning near-optimal cost-sensitive decision policy for object detection.

Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection