Weighted Hausdorff Distance: A Loss Function For Object Localization

@article{Ribera2018WeightedHD,
  title={Weighted Hausdorff Distance: A Loss Function For Object Localization},
  author={Javier Ribera and David G{\"u}era and Yuhao Chen and Edward J. Delp},
  journal={ArXiv},
  year={2018},
  volume={abs/1806.07564}
}
Recent advances in Convolutional Neural Networks (CNN) have achieved remarkable results in localizing objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects. In this paper, we address the task of estimating object locations without annotated bounding boxes, which are typically hand-drawn and time consuming to label. We propose a loss function that can be used in any Fully Convolutional Network (FCN) to… CONTINUE READING
11
Twitter Mentions

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • We report an average precision and recall of 94% for the three datasets, and an average location error of 6 pixels in 256x256 images.

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

Geometry-Aware End-to-End Skeleton Detection

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 57 REFERENCES

Mean Shift: A Robust Approach Toward Feature Space Analysis

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2002
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

The expectation-maximization algorithm

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Mask R-CNN.

  • IEEE transactions on pattern analysis and machine intelligence
  • 2018
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2015
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Fast R-CNN

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Body Structure Aware Deep Crowd Counting

  • IEEE Transactions on Image Processing
  • 2018
VIEW 1 EXCERPT

Deepwheat: Estimating phenotypic traits from crop 18 J

S. Aich, I. Ahmed, +6 authors S. Shirtliffe
  • Ribera et al. images with deep learning. Proceedings of the IEEE Winter Conference on Applications of Computer Vision
  • 2018
VIEW 1 EXCERPT

Deep Learning for Medical Image Analysis

S. K. Zhou, H. Greenspan, D. Shen
  • Academic Press, London, United Kingdom
  • 2017
VIEW 1 EXCERPT