Reinforcement learning for visual object detection

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review

99 Citeringar (SciVal)

Sammanfattning

One of the most widely used strategies for visual object detection is based on exhaustive spatial hypothesis search. While methods like sliding windows have been successful and effective for many years, they are still brute-force, independent of the image content and the visual category being searched. In this paper we present principled sequential models that accumulate evidence collected at a small set of image locations in order to detect visual objects effectively. By formulating sequential search as reinforcement learning of the search policy (including the stopping condition), our fully trainable model can explicitly balance for each class, specifically, the conflicting goals of exploration - sampling more image regions for better accuracy-, and exploitation - stopping the search efficiently when sufficiently confident about the target's location. The methodology is general and applicable to any detector response function. We report encouraging results in the PASCAL VOC 2012 object detection test set showing that the proposed methodology achieves almost two orders of magnitude speed-up over sliding window methods.

Originalspråkengelska
Titel på värdpublikation2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
FörlagIEEE Computer Society
Sidor2894-2902
Antal sidor9
Volym2016-January
ISBN (elektroniskt)9781467388511
DOI
StatusPublished - 2016
Evenemang2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, USA
Varaktighet: 2016 juni 262016 juli 1

Konferens

Konferens2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Land/TerritoriumUSA
OrtLas Vegas
Period2016/06/262016/07/01

Ämnesklassifikation (UKÄ)

  • Datorseende och robotik (autonoma system)

Fingeravtryck

Utforska forskningsämnen för ”Reinforcement learning for visual object detection”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här