New Results on Sparse Autoencoders for Posture Classification and Segmentation

Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN’20), pages 187--192 - Oct 2020.
Associated documents : 2020JirakWermterESANN.pdf [158Ko]  
This paper is a sequel on posture recognition using sparse autoencoders. We conduct experiments on a posture dataset and show that shallow sparse autoencoders achieve even better performance compared to a convolutional neural network, state-of-the-art model for recognition tasks. Also, our results support robust image representation from the autoencoder model rendering further finetuning unnecessary. Finally, we suggest using sparse autoencoders for image segmentation.

 

@InProceedings\{JW20,
  author       = "Jirak, Doreen and Wermter, Stefan",
  title        = "New Results on Sparse Autoencoders for Posture Classification and Segmentation",
  booktitle    = "Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN’20)",
  series       = "European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",
  pages        = "187--192",
  month        = "Oct",
  year         = "2020",
  url          = "https://www2.informatik.uni-hamburg.de/wtm/publications/2020/JW20/2020JirakWermterESANN.pdf"
}

» Doreen Jirak
» Stefan Wermter