Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  What Makes for Effective Detection Proposals?

Hosang, J., Benenson, R., Dollár, P., & Schiele, B. (2015). What Makes for Effective Detection Proposals? Retrieved from http://arxiv.org/abs/1502.05082.

Item is

Dateien

einblenden: Dateien
ausblenden: Dateien
:
1502.05082.pdf (Preprint), 5MB
Name:
1502.05082.pdf
Beschreibung:
File downloaded from arXiv at 2015-02-19 17:03 updated PAMI submission
OA-Status:
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Hosang, Jan1, Autor           
Benenson, Rodrigo1, Autor           
Dollár, Piotr2, Autor
Schiele, Bernt1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Zusammenfassung: Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL and ImageNet, and impact on DPM and R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detector performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2015-02-172015
 Publikationsstatus: Online veröffentlicht
 Seiten: 16 p.
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: arXiv: 1502.05082
URI: http://arxiv.org/abs/1502.05082
BibTex Citekey: Hosang2015arXiv
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: