articleProceedings of the AAAI Conference on Artificial IntelligenceJun 28, 2022DIAMOND OA

Shape-Adaptive Selection and Measurement for Oriented Object Detection

LHLiping HouKLKe LüJXJian XueYLYuqiu Li

University of Chinese Academy of Sciences · Peng Cheng Laboratory

Indexed incrossref

Abstract

The development of detection methods for oriented object detection remains a challenging task. A considerable obstacle is the wide variation in the shape (e.g., aspect ratio) of objects. Sample selection in general object detection has been widely studied as it plays a crucial role in the performance of the detection method and has achieved great progress. However, existing sample selection strategies still overlook some issues: (1) most of them ignore the object shape information; (2) they do not make a potential distinction between selected positive samples; and (3) some of them can only be applied to either anchor-free or anchor-based methods and cannot be used for both of them simultaneously. In this…

Citation impact

269
total citations
FWCI
15.05
Percentile
100%
References
76
Citations per year

Authors

4

Topics & keywords

Topics
Keywords
  • Obstacle
  • Computer science
  • Selection (genetic algorithm)
  • Object (grammar)
  • Sample (material)
  • Task (project management)
  • Object detection
  • Artificial intelligence
No related works found for this paper.

Funding