Object Detection with Discriminatively Trained Part-Based Models

  • Authors:

  • Pedro F. Felzenszwalb;Ross B. Girshick;David McAllester;Deva Ramanan

  • Affiliations:

  • University of Chicago, Chicago;University of Chicago, Chicago;Toyota Technological Institute at Chicago, Chicago;University of California, Irvine, Irvine

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 2010

Quantified Score

Hi-index 0.18

Visualization

Abstract

We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI--SVM in terms of latent variables. A latent SVM is semiconvex, and the training problem becomes convex once latent information is specified for the positive examples. This leads to an iterative training algorithm that alternates between fixing latent values for positive examples and optimizing the latent SVM objective function.