Learning to validate the quality of detected landmarks

Wolfgang Fuhl, Enkelejda Kasneci

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We present a new loss function for the validation of image landmarks detected via Convolutional Neural Networks (CNN). The network learns to estimate how accurate its landmark estimation is. This loss function is applicable to all regression-based location estimations and allows the exclusion of unreliable landmarks from further processing. In addition, we formulate a novel batch balancing approach which weights the importance of samples based on their produced loss. This is done by computing a probability distribution mapping on an interval from which samples can be selected using a uniform random selection scheme. We conducted experiments on the 300W, AFLW, and WFLW facial landmark datasets. In the first experiments, the influence of our batch balancing approach is evaluated by comparing it against uniform sampling. In addition, we evaluated the impact of the validation loss on the landmark accuracy based on uniform sampling. The last experiments evaluate the correlation of the validation signal with the landmark accuracy. All experiments were performed for all three datasets.

Original languageEnglish
Title of host publication12th International Conference on Machine Vision, ICMV 2019
EditorsWolfgang Osten, Dmitry Nikolaev, Jianhong Zhou
ISBN (Electronic)9781510636439
StatePublished - 2020
Externally publishedYes
Event12th International Conference on Machine Vision, ICMV 2019 - Amsterdam, Netherlands
Duration: 16 Nov 201918 Nov 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


Conference12th International Conference on Machine Vision, ICMV 2019


  • Batch creation
  • Deep learning
  • Landmark detection
  • Landmark validation


Dive into the research topics of 'Learning to validate the quality of detected landmarks'. Together they form a unique fingerprint.

Cite this