Object Bank: An Object-Level Image Representation for High-Level Visual Recognition

  • Authors:

  • Li-Jia Li;Hao Su;Yongwhan Lim;Li Fei-Fei

  • Affiliations:

  • Yahoo! Research, Sunnyvale, USA 94089;Computer Science Department, Stanford University, Stanford, USA 94305;Computer Science Department, Stanford University, Stanford, USA 94305;Computer Science Department, Stanford University, Stanford, USA 94305

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

It is a remarkable fact that images are related to objects constituting them. In this paper, we propose to represent images by using objects appearing in them. We introduce the novel concept of object bank (OB), a high-level image representation encoding object appearance and spatial location information in images. OB represents an image based on its response to a large number of pre-trained object detectors, or `object filters', blind to the testing dataset and visual recognition task. Our OB representation demonstrates promising potential in high level image recognition tasks. It significantly outperforms traditional low level image representations in image classification on various benchmark image datasets by using simple, off-the-shelf classification algorithms such as linear SVM and logistic regression. In this paper, we analyze OB in detail, explaining our design choice of OB for achieving its best potential on different types of datasets. We demonstrate that object bank is a high level representation, from which we can easily discover semantic information of unknown images. We provide guidelines for effectively applying OB to high level image recognition tasks where it could be easily compressed for efficient computation in practice and is very robust to various classifiers.