DASA: Domain adaptation in stacked autoencoders using systematic dropout

@article{Roy2015DASADA,
  title={DASA: Domain adaptation in stacked autoencoders using systematic dropout},
  author={Abhijit Guha Roy and D. Sheet},
  journal={2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)},
  year={2015},
  pages={735-739}
}
Domain adaptation deals with adapting behaviour of machine learning based systems trained using samples in source domain to their deployment in target domain where the statistics of samples in both domains are dissimilar The task of directly training or adapting a learner in the target domain is challenged by lack of abundant labeled samples. In this paper we propose a technique for domain adaptation in stacked autoencoder (SAE) based deep neural networks (DNN) performed in two stages: (i… Expand
13 Citations
Deep neural ensemble for retinal vessel segmentation in fundus images towards achieving label-free angiography
  • 45
  • PDF
COMA-boost: co-operative multi agent AdaBoost
Semi-supervised Transfer Learning for Convolutional Neural Networks for Glaucoma Detection
  • 9
Generative Adversarial Learning for Reducing Manual Annotation in Semantic Segmentation on Large Scale Miscroscopy Images: Automated Vessel Segmentation in Retinal Fundus Image as Test Case
  • 41
  • PDF
Deep Learning based Computer-Aided Diagnosis Systems for Diabetic Retinopathy: A Survey
  • 35
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 14 REFERENCES
Marginalized Denoising Autoencoders for Domain Adaptation
  • 626
  • PDF
Marginalized Denoising Autoencoder via Graph Regularization for Domain Adaptation
  • 8
  • PDF
Fast Easy Unsupervised Domain Adaptation with Marginalized Structured Dropout
  • 23
  • PDF
Autoencoder-based Unsupervised Domain Adaptation for Speech Emotion Recognition
  • 168
Real-World Font Recognition Using Deep Network and Domain Adaptation
  • 7
  • PDF
Dropout: a simple way to prevent neural networks from overfitting
  • 22,413
  • PDF
A Survey on Transfer Learning
  • 10,532
  • PDF
Learning Deep Architectures for AI
  • 6,587
  • PDF
Retinal Imaging and Image Analysis.
  • 562
  • PDF
Autoencoderbased unsupervised domain adaptation for speech emotion recognition
  • IEEE Signal Process. Let.,
  • 2014
...
1
2
...