Continual learning via knowledge distillation achieves SOTA 74.28% accuracy on new compound facial expression classes and 100% in one-shot learning.
Densely connected convolutional networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
LAD generates diverse adversarial examples in latent space by perturbing along normals to an SVM-defined decision boundary and uses them for adversarial training to improve DNN robustness.
Introduces CSEN, a non-iterative network bridging sparse representation and deep learning, for Covid-19 detection from X-ray images with limited training data.
citing papers explorer
-
Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic Features
Continual learning via knowledge distillation achieves SOTA 74.28% accuracy on new compound facial expression classes and 100% in one-shot learning.
-
Latent Adversarial Defence with Boundary-guided Generation
LAD generates diverse adversarial examples in latent space by perturbing along normals to an SVM-defined decision boundary and uses them for adversarial training to improve DNN robustness.
-
Convolutional Sparse Support Estimator Based Covid-19 Recognition from X-ray Images
Introduces CSEN, a non-iterative network bridging sparse representation and deep learning, for Covid-19 detection from X-ray images with limited training data.