1 code implementation • 27 Aug 2021 • Ammar Mansoor Kamoona, Amirali Khodadadian Gostar, Alireza Bab-Hadiashar, Reza Hoseinnezhad
Experimental results show the outstanding performance of our proposed approach compared to the state-of-the-art methods, and the proposed RFS energy outperforms the state-of-the-art in the few shot learning settings.
Ranked #63 on Anomaly Detection on MVTec AD
no code implementations • 3 Feb 2021 • Ammar Mansoor Kamoona, Amirali Khodadadian Gostar, Alireza Bab-Hadiashar, Reza Hoseinnezhad
The results show that using point pattern features, such as SIFT as data points for random finite set-based anomaly detection achieves the most consistent defect detection accuracy on the MVTec-AD dataset.
1 code implementation • 3 Jul 2020 • Ammar Mansoor Kamoona, Amirali Khodadadian Gosta, Alireza Bab-Hadiashar, Reza Hoseinnezhad
The proposed approach uses both abnormal and normal video clips during the training phase which is developed in the multiple instance framework where we treat video as a bag and video clips as instances in the bag.
Anomaly Detection In Surveillance Videos Multiple Instance Learning +1