3 papers
cs.CV2021
Deep Visual Anomaly detection with Negative Learning
Jin-Ha Lee, Marcella Astrid, Muhammad Zaigham Zaheer +1
With the increase in the learning capability of deep convolution-based architectures, various applications of such models have been proposed over time. In the field of anomaly dete…
cs.CV2021
Cleaning Label Noise with Clusters for Minimally Supervised Anomaly Detection
Muhammad Zaigham Zaheer, Jin-ha Lee, Marcella Astrid +2
Learning to detect real-world anomalous events using video-level annotations is a difficult task mainly because of the noise present in labels. An anomalous labelled video may actu…
cs.CV2020
Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm
Muhammad Zaigham Zaheer, Jin-ha Lee, Marcella Astrid +1
A popular method for anomaly detection is to use the generator of an adversarial network to formulate anomaly scores over reconstruction loss of input. Due to the rare occurrence o…