Details

Autor(en) / Beteiligte

• You, Zhiyuan
• Yang, Kai
• Luo, Wenhan
• Cui, Lei
• Zheng, Yu
• Le, Xinyi

Titel

ADTR: Anomaly Detection Transformer with Feature Reconstruction

Ist Teil von

• Neural Information Processing, p.298-310

Ort / Verlag

Cham: Springer International Publishing

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Anomaly detection with only prior knowledge from normal samples attracts more attention because of the lack of anomaly samples. Existing CNN-based pixel reconstruction approaches suffer from two concerns. First, the reconstruction source and target are raw pixel values that contain indistinguishable semantic information. Second, CNN tends to reconstruct both normal samples and anomalies well, making them still hard to distinguish. In this paper, we propose Anomaly Detection TRansformer (ADTR) to apply a transformer to reconstruct pre-trained features. The pre-trained features contain distinguishable semantic information. Also, the adoption of transformer limits to reconstruct anomalies well such that anomalies could be detected easily once the reconstruction fails. Moreover, we propose novel loss functions to make our approach compatible with the normal-sample-only case and the anomaly-available case with both image-level and pixel-level labeled anomalies. The performance could be further improved by adding simple synthetic or external irrelevant anomalies. Extensive experiments are conducted on anomaly detection datasets including MVTec-AD and CIFAR-10. Our method achieves superior performance compared with all baselines.