Diagnosing error in object detectors

Authors:
Derek Hoiem;Yodsawalai Chodpathumwan;Qieyun Dai
Affiliations:
Department of Computer Science, University of Illinois at Urbana-Champaign;Department of Computer Science, University of Illinois at Urbana-Champaign;Department of Computer Science, University of Illinois at Urbana-Champaign
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Year:
2012

Citing 10
Cited 1

Evaluation of Interest Point Detectors

International Journal of Computer Vision - Special issue on a special section on visual surveillance
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Overview of the Face Recognition Grand Challenge

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
The Pascal Visual Object Classes (VOC) Challenge

International Journal of Computer Vision
Object Detection with Discriminatively Trained Part-Based Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
A comparative evaluation of interest point detectors and local descriptors for visual SLAM

Machine Vision and Applications
Multiresolution models for object detection

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Unbiased look at dataset bias

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
The truth about cats and dogs

ICCV '11 Proceedings of the 2011 International Conference on Computer Vision

Coloring Action Recognition in Still Images

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives. In particular, we examine effects of occlusion, size, aspect ratio, visibility of parts, viewpoint, localization error, and confusion with semantically similar objects, other labeled objects, and background. We analyze two classes of detectors: the Vedaldi et al. multiple kernel learning detector and different versions of the Felzenszwalb et al. detector. Our study shows that sensitivity to size, localization error, and confusion with similar objects are the most impactful forms of error. Our analysis also reveals that many different kinds of improvement are necessary to achieve large gains, making more detailed analysis essential for the progress of recognition research. By making our software and annotations available, we make it effortless for future researchers to perform similar analysis.