articleJun 1, 2019Closed access

Region Proposal by Guided Anchoring

Chinese University of Hong Kong · Amazon (Germany) · +1 more institution

Indexed incrossref

Abstract

Region anchors are the cornerstone of modern object detection techniques. State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios. In this paper, we revisit this foundational stage. Our study shows that it can be done much more effectively and efficiently. Specifically, we present an alternative scheme, named Guided Anchoring, which leverages semantic features to guide the anchoring. The proposed method jointly predicts the locations where the center of objects of interest are likely to exist as well as the scales and aspect ratios at different locations. On top of predicted anchor shapes,…

Citation impact

682
total citations
FWCI
46.03
Percentile
100%
References
49
Citations per year

Authors

5

Topics & keywords

Keywords
  • Anchoring
  • Computer science
  • Object detection
  • Feature (linguistics)
  • Set (abstract data type)
  • Detector
  • Code (set theory)
  • Scheme (mathematics)
UN Sustainable Development Goals
  • Life below water
No related works found for this paper.