Balancing Feature Imitation and Knowledge Consistency for Improving Anomaly Detection

Zi Wang*, Katsuya Hotta, Kohei Nakazawa, Chao Zhang, Jun Yu

*この論文の責任著者

研究成果: 書籍の章/レポート/会議録会議への寄与査読

抄録

Unsupervised anomaly detection methods are essential for addressing the challenge of accessing anomalous data in real-world scenarios. Among these methods, student-teacher framework-based methods have garnered increasing attention due to their low latency and competitive performance. This framework leverages the knowledge disparities between the teacher and student networks, particularly their differences in feature extraction capabilities, for anomaly detection. In this paper, we propose not only to leverage the process of feature imitation for anomaly scoring but also to exploit the consistency among neighboring layer groups to enhance anomaly detection performance. Experiment shows that our model can significantly improve anomaly detection performance by incorporating a knowledge consistency term into the scoring process.

本文言語英語
ホスト出版物のタイトルGCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1409-1410
ページ数2
ISBN(電子版)9798350355079
DOI
出版ステータス出版済み - 2024
イベント13th IEEE Global Conference on Consumer Electronic, GCCE 2024 - Kitakyushu, 日本
継続期間: 2024/10/292024/11/01

出版物シリーズ

名前GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics

学会

学会13th IEEE Global Conference on Consumer Electronic, GCCE 2024
国/地域日本
CityKitakyushu
Period2024/10/292024/11/01

ASJC Scopus 主題領域

  • 人工知能
  • コンピュータ ビジョンおよびパターン認識
  • 人間とコンピュータの相互作用
  • 信号処理
  • 電子工学および電気工学
  • メディア記述
  • 器械工学

フィンガープリント

「Balancing Feature Imitation and Knowledge Consistency for Improving Anomaly Detection」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル