Object Detection with Discriminatively Trained Part-Based Models

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.

1 Introduction

Object recognition is one of the fundamental challenges in computer vision. In this paper, we consider the problem of detecting and localizing generic objects from categories such as people or cars in static images. This is a difficult problem because objects in such categories can vary greatly in appearance. Variations arise not only from changes in illumination and viewpoint, but also due to nonrigid deformations and intraclass variability in shape and other visual properties. For example, people wear different clothes and take a variety of poses, while cars come in various shapes and colors.