Steerable part models
- 1 June 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3226-3233
- https://doi.org/10.1109/cvpr.2012.6248058
Abstract
We describe a method for learning steerable deformable part models. Our models exploit the fact that part templates can be written as linear filter banks. We demonstrate that one can enforce steerability and separability during learning by applying rank constraints. These constraints are enforced with a coordinate descent learning algorithm, where each step can be solved with an off-the-shelf structured SVM solver. The resulting models are orders of magnitude smaller than their counterparts, greatly simplifying learning and reducing run-time computation. Limiting the degrees of freedom also reduces overfitting, which is useful for learning large part vocabularies from limited training data. We learn steerable variants of several state-of-the-art models for object detection, human pose estimation, and facial landmark estimation. Our steerable models are smaller, faster, and often improve performance.Keywords
This publication has 18 references indexed in Scilit:
- Recognition using visual phrasesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Shared parts for deformable part-based modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- A coarse-to-fine approach for fast deformable object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Articulated pose estimation with flexible mixtures-of-partsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Modeling Appearances with Low-Rank SVMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Sharing Visual Features for Multiclass and Multiview Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Video Google: Efficient Visual Search of VideosLecture Notes in Computer Science, 2006
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Efficient deformable filter banksIEEE Transactions on Signal Processing, 1998
- Deformable kernels for early visionIeee Transactions On Pattern Analysis and Machine Intelligence, 1995