English

Slender Object Detection: Diagnoses and Improvements

Computer Vision and Pattern Recognition 2021-04-08 v4

Abstract

In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely \textbf{slender objects}. In real-world scenarios, slender objects are actually very common and crucial to the objective of a detection system. However, this type of objects has been largely overlooked by previous object detection algorithms. Upon our investigation, for a classical object detection method, a drastic drop of 18.9%18.9\% mAP on COCO is observed, if solely evaluated on slender objects. Therefore, we systematically study the problem of slender object detection in this work. Accordingly, an analytical framework with carefully designed benchmark and evaluation protocols is established, in which different algorithms and modules can be inspected and compared. \New Our study reveals that effective slender object detection can be achieved ~\textbf{with none of} (1) anchor-based localization; (2) specially designed box representations. Instead, \textbf{the critical aspect of improving slender object detection is feature adaptation}. It identifies and extends the insights of existing methods that are previously underexploited. Furthermore, we propose a feature adaption strategy that achieves clear and consistent improvements over current representative object detection methods.

Keywords

Cite

@article{arxiv.2011.08529,
  title  = {Slender Object Detection: Diagnoses and Improvements},
  author = {Zhaoyi Wan and Yimin Chen and Sutao Deng and Kunpeng Chen and Cong Yao and Jiebo Luo},
  journal= {arXiv preprint arXiv:2011.08529},
  year   = {2021}
}
R2 v1 2026-06-23T20:18:37.131Z