Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
This work addresses multi-class anomaly detection for applications needing to handle multiple object categories, representing an incremental improvement over prior unified models.
The paper tackles the problem of multi-class anomaly detection by introducing MINT-AD, a model that uses class labels to reduce inter-class interference, and it outperforms existing unified models on multiple datasets.
In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Although several papers have designed unified models for this task, they often overlook the utility of class labels, a potent tool for mitigating inter-class interference. To address this issue, we introduce a Multi-class Implicit Neural representation Transformer for unified Anomaly Detection (MINT-AD), which leverages the fine-grained category information in the training stage. By learning the multi-class distributions, the model generates class-aware query embeddings for the transformer decoder, mitigating inter-class interference within the reconstruction model. Utilizing such an implicit neural representation network, MINT-AD can project category and position information into a feature embedding space, further supervised by classification and prior probability loss functions. Experimental results on multiple datasets demonstrate that MINT-AD outperforms existing unified training models.