Sharing features: efficient boosting procedures for multiclass object detection

@inproceedings{Torralba2004SharingFE,
  title={Sharing features: efficient boosting procedures for multiclass object detection},
  author={Antonio Torralba and Kevin P. Murphy and William T. Freeman},
  booktitle={CVPR 2004},
  year={2004}
}
We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, which can be slow and require much training data. We present a multi-class boosting procedure (joint boosting) that reduces both the computational and sample complexity, by finding common features that can be shared across the classes. The detectors for each class are trained jointly, rather than… 
Joint learning for multi-class object detection
TLDR
This work proposes to show the advantage of grouping similar object classes into a hierarchical structure, and shows that this approach improves detection performance compared to a baseline approach.
Contour-based learning for object detection
TLDR
The major contributions are the application of boosted local contour-based features for object detection in a partially supervised learning framework, and an efficient new boosting procedure for simultaneously selecting features and estimating per-feature parameters.
Kernel Sharing With Joint Boosting For Multi-Class Concept Detection
TLDR
This paper proposed a new framework for multi-class concept detection based on kernel sharing and joint learning for discriminative kernel-based classification, and constructed multi-resolution visual vocabularies by hierarchical clustering and computed kernels based on spatial matching.
Generic object recognition with regional statistical models and layer joint boosting
Multiclass object detection system in imaging sensor network using Haar-like features and Joint-Boosting algorithm
TLDR
Though the proposed scheme is validated for car and pedestrian classes, the training and detection techniques can be generalised for any object class and the benefits of illumination normalisation or variance normalisation technique used to neutralise the effect of changing lighting conditions are explored.
Multiple Object Class Detection with a Generative Model
TLDR
The performance of the proposed multi-object class detection approach is competitive to state of the art approaches dedicated to a single object class recognition problem.
Chapter 8 Object Detection
TLDR
This chapter focuses on those methods that use the cascade classifier structure together with ensemble learning methods (e.g., AdaBoost), and presents the first face detection system that could both run in real-time and achieve high detection accuracy.
Parameter Sensitive Detectors
TLDR
A new formulation is proposed, where the detectors themselves are associated with continuous parameters, and reside in a parameterized function space, and the underlying parameters for object variations can be learned from training data in an unsupervised manner.
Multi-class object detection by part based approach
TLDR
An efficient method to detect multiple objects in multiple views by part based approach in computer vision adapted to detect and classify the multiple parts of objects as car/person in order to overcome the occlusion.
Improvements of Object Detection Using Boosted Histograms
TLDR
A method for object detection that combines AdaBoost learning with local histogram features that outperforms all methods reported in [5] for 7 out of 8 detection tasks and four object classes.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
Sequential Learning of Reusable Parts for Object Detection
TLDR
Initial experiments on learning to detect several hundred LTEXsymbols are encouraging, and significant further gains in efficiency in representation, error rates and computation can be realized if the family of detectors is constructed from common parts.
Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection
TLDR
A novel set of rotated haar-like features is introduced that significantly enrich the simple features of [6] and can also be calculated efficiently and present a through analysis of different boosting algorithms and weak classifiers on the detection performance and computational complexity.
A Trainable System for Object Detection
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes an object class in
Object recognition with informative features and linear classification
TLDR
The results show that by maximizing the individual information of the features, it is possible to obtain efficient classification by a simple linear separating rule, as well as more efficient learning.
Object recognition using boosted discriminants
  • S. Mahamud, M. Hebert, Jianbo Shi
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
TLDR
This work approaches the task of object discrimination as that of learning efficient "codes" for each object class in terms of responses to a set of chosen discriminants in an energy minimization framework and derives an iterative solution that alternates between the solutions for two generalized eigenproblems.
Robust Real-Time Face Detection
TLDR
A new image representation called the “Integral Image” is introduced which allows the features used by the detector to be computed very quickly and a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions.
A Bayesian approach to unsupervised one-shot learning of object categories
TLDR
This work presents a method for learning object categories from just a few images, based on incorporating "generic" knowledge which may be obtained from previously learnt models of unrelated categories, in a variational Bayesian framework.
Analyzing appearance and contour based methods for object categorization
  • B. Leibe, B. Schiele
  • Computer Science
    2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
TLDR
A new database specifically tailored to the task of object categorization is presented, which contains high-resolution color images of 80 objects from 8 different categories and is used to analyze the performance of several appearance and contour based methods.
Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers
TLDR
A general method for combining the classifiers generated on the binary problems is proposed, and a general empirical multiclass loss bound is proved given the empirical loss of the individual binary learning algorithms.
Object recognition from local scale-invariant features
  • D. Lowe
  • Computer Science
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
...
1
2
3
...