Ensemble of exemplar-SVMs for object detection and beyond

  • Authors:

  • Tomasz Malisiewicz;Abhinav Gupta;Alexei A. Efros

  • Affiliations:

  • Carnegie Mellon University, USA;Carnegie Mellon University, USA;Carnegie Mellon University, USA

  • Venue:
  • ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

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.