Diagnosing Error in Object Detectors

  title={Diagnosing Error in Object Detectors},
  author={Derek Hoiem and Yodsawalai Chodpathumwan and Qieyun Dai},
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… CONTINUE READING
Highly Influential
This paper has highly influenced 26 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 294 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 188 extracted citations

295 Citations

Citations per Year
Semantic Scholar estimates that this publication has 295 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 30 references

CaltechUCSD Birds 200

  • P. Welinder, S. Branson, +4 authors P. Perona
  • Technical Report CNS-TR-2010-001, California…
  • 2010

Similar Papers

Loading similar papers…