Authors:
Yusuke Hatae
1
;
Qingpu Yang
2
;
Muhammad Fikko Fadjrimiratno
2
;
Yuanyuan Li
1
;
Tetsu Matsukawa
1
and
Einoshin Suzuki
1
Affiliations:
1
ISEE, Kyushu University, Fukuoka, 819-0395, Japan
;
2
SLS, Kyushu University, Fukuoka, 819-0395, Japan
Keyword(s):
Anomaly Detection, Anomalous Image Region Detection, Deep Captioning, Word Embedding.
Abstract:
In this paper we propose a one-class anomalous region detection method from an image based on deep captioning. Such a method can be installed on an autonomous mobile robot, which reports anomalies from observation without any human supervision and would interest a wide range of researchers, practitioners, and users. In addition to image features, which were used by conventional methods, our method exploits recent advances in deep captioning, which is based on deep neural networks trained on a large-scale data on image - caption pairs, enabling anomaly detection in the semantic level. Incremental clustering is adopted so that the robot is able to model its observation into a set of clusters and report substantially new observations as anomalies. Extensive experiments using two real-world data demonstrate the superiority of our method in terms of recall, precision, F measure, and AUC over the traditional approach. The experiments also show that our method exhibits excellent learning cu
rve and low threshold dependency.
(More)