Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity.
Yi Xiang Marcus TanPenny ChongJiamei SunYuval EloviciAlexander BinderPublished in: CoRR (2020)
Keyphrases
- detection algorithm
- adaboost classifier
- feature set
- decision trees
- denoising
- feature weights
- detection rate
- haar features
- shot boundary detection
- training set
- discriminative classifiers
- object detection
- feature selection
- test set
- anomaly detection
- training data
- video sequences
- support vector
- image features
- shot change detection
- feature ranking
- weak classifiers
- natural images
- event detection
- false positives
- detection method
- training examples
- video content
- feature subset
- multiple features
- input features
- change detection
- video indexing
- artificial neural networks
- visual features
- naive bayes