In this work, we show that Relation Graph augmented Learning (RGL) can improve the performance of few-shot natural language understanding tasks.
Unsupervised anomaly detection methods are at the forefront of industrial anomaly detection efforts and have made notable progress.
While these unsupervised anomaly detection methods offer convenience, they also overlook the crucial prior information embedded within anomalous samples.
Point-level weakly-supervised temporal action localization (PWTAL) aims to localize actions with only a single timestamp annotation for each action instance.
The replay attack detection problem is studied from a new perspective based on parity space method in this paper.
By eliminating unnecessary features and reconstructing the semantic relations among discriminative features, our SFI-Net has achieved satisfying performance.