Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
data_augmentation [2018/05/21 16:38]
admin
data_augmentation [2018/06/04 22:14] (current)
admin
Line 129: Line 129:
 https://​arxiv.org/​abs/​1805.06962 Counterexample-Guided Data Augmentation https://​arxiv.org/​abs/​1805.06962 Counterexample-Guided Data Augmentation
  
-Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our framework include a counterexample generator, which produces data items that are misclassified by the model and error tables, a novel data structure that stores information pertaining to misclassifications. Error tables can be used to explain the model'​s vulnerabilities and are used to efficiently generate counterexamples for augmentation. We show the efficacy of the proposed framework by comparing it to classical augmentation techniques on a case study of object detection in autonomous driving based on deep neural networks.+Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our framework include a counterexample generator, which produces data items that are misclassified by the model and error tables, a novel data structure that stores information pertaining to misclassifications. Error tables can be used to explain the model'​s vulnerabilities and are used to efficiently generate counterexamples for augmentation. We show the efficacy of the proposed framework by comparing it to classical augmentation techniques on a case study of object detection in autonomous driving based on deep neural networks. ​https://​github.com/​dreossi/​analyzeNN 
 + 
 +https://​arxiv.org/​abs/​1805.12018 Generalizing to Unseen Domains via Adversarial Data Augmentation 
 + 
 +Only using training data from the source domain, we propose an iterative procedure that augments the dataset with examples from a fictitious target domain that is "​hard"​ under the current model. We show that our iterative scheme is an adaptive data augmentation method where we append adversarial examples at each iteration. 
 + 
 +https://​ai.googleblog.com/​2018/​06/​improving-deep-learning-performance.html ​