Improving object proposals with top-down cues

Wei Li, Hongliang Li, Bing Luo, Hengcan Shi, Qingbo Wu, King Ngi Ngan

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Abstract

The generation of object proposals plays an important role in object detection. Most existing methods produce object proposals by using bottom-up cues, such as closed contour or superpixel. In this paper, we propose a novel method to improve the ranking of object proposals by combining bottom-up cues with top-down information of objectivity. Firstly, we utilize the bottom-up method to generate initial object proposals of the given test image. Then we retrieve its top-k similar images from training images set. Considering both appearance and spatial similarity between initial object proposals and the ground truth bounding boxes of these top-k similar images, we obtain the top-down guided scores of initial object proposals. Finally, the refined score of each initial object proposal is modeled as a fusion of the bottom-up score and the top-down score. Experiments show that our method achieves better performance compared with the state-of-art on the Pascal VOC2007 dataset.

Original languageEnglish
Pages (from-to)20-27
Number of pages8
JournalSignal Processing: Image Communication
Volume56
DOIs
Publication statusPublished - Aug 2017
Externally publishedYes

Keywords

  • Object detection
  • Object proposals
  • Object recognition

Cite this