ICCV 2011 一篇文章：Ensemble of Exemplar-SVMs

今天偶然看到了一篇ICCV 2011的文章，Ensemble of Exemplar-SVMs for Object Detection and Beyond，还没有细读，但是看了题目我就吸引住了，因为和自己正在思考的一个idea类似，也是用模板集成的方法，只是搜索模板的方法可能不同，集成方法可能不同，但是我要继续思考下要不要做，还有没有真是的以及和价值。

不过，应该可以做的。

废话少说，这篇用线性svm训练object模板，每个类别都会训练好几个模板，然后进行集成，细节论文中有，这种思想感觉比较暴力，自古模板法效果就不错，最典型的就是“P. F. Felzenszwalb, R. B. Girschick, D. McCallester, and D. Ramanan.
Object detection with discriminatively trained part based
models. PAMI, 2010”这篇文章将到的特别暴力的模板法，而且效率很低。

不过用这篇文章作者说效率要比Felzenszwalb的高很多很多，而且准确性等方面也好很多很多，出奇的好。

而且还有Code可以用，作者的后两位ie，特别是Alexei A. Efros (Carnegie Mellon University)，也是领域的大牛，有多牛就不用说了。Abhinav Gupta (Carnegie Mellon University)这两年在CVPR ICCV都有大量文章，有这些人参与，好文章当然会有了。

 

People

• Tomasz Malisiewicz (Carnegie Mellon University)
• Abhinav Gupta (Carnegie Mellon University)
• Alexei A. Efros (Carnegie Mellon University)

Abstract

This paper proposes a conceptually simple but surprisingly powerful method which combines the effectiveness of a discriminative object detector with the explicit correspondence offered by a nearest-neighbor approach. The method is based on training a separate linear SVM classifier for every exemplar in the training set. Each of these Exemplar-SVMs is thus defined by a single positive instance and millions of negatives. While each detector is quite specific to its exemplar, we empirically observe that an ensemble of such Exemplar-SVMs offers surprisingly good generalization. Our performance on the PASCAL VOC detection task is on par with the much more complex latent part-based model of Felzenszwalb et al., at only a modest computational cost increase. But the central benefit of our approach is that it creates an explicit association between each detection and a single training exemplar. Because most detections show good alignment to their associated exemplar, it is possible to transfer any available exemplar meta-data (segmentation, geometric structure, 3D model, etc.) directly onto the detections, which can then be used as part of overall scene understanding.

Paper download and Citation

Tomasz Malisiewicz, Abhinav Gupta, Alexei A. Efros. Ensemble of Exemplar-SVMs for Object Detection and Beyond . In ICCV, 2011. PDF [BibTeX]

Matlab Code (Beta Version)

Source code for the entire Exemplar-SVM infrastructure (large-scale training using a cluster, fast detection, etc.) is available for download below. To download the source code, choose an option below:
Exemplar-SVM tarball
Exemplar-SVM zipfile

 

You can also directly navigate to the Exemplar-SVM Github project page, which has download instructions, a wiki, and additional starter-guides.

https://github.com/quantombone/exemplarsvm

NOTE: A more user-friendly version of the code along with the pre-trained PASCAL VOC 2007 exemplar models will be made available before the ICCV 2011 Conference.