Object Detection with Discriminatively Trained Part Based Models

DMCA

Object Detection with Discriminatively Trained Part Based Models

Cached

Download Links

by Pedro F. Felzenszwalb , Ross B. Girshick , David McAllester , Deva Ramanan

Citations:

1422 - 49 self

BibTeX

@MISC{Felzenszwalb_objectdetection,
    author = {Pedro F. Felzenszwalb and Ross B. Girshick and David McAllester and Deva Ramanan},
    title = {Object Detection with Discriminatively Trained Part Based Models},
    year = {}
}

OpenURL

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 datasets. 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 semi-convex 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.

Keyphrases

object detection discriminatively trained part latent svm positive example deformable part model discriminative training new method object detection system multiscale deformable part model latent svm objective function data-mining hard negative example latent information iterative training algorithm difficult benchmark latent variable pascal object detection challenge latent value variable object class training problem state-of-the-art result pascal datasets margin-sensitive approach

DMCA