未經訓練的神經網絡在異常檢測中能走多遠?從表格到像素
How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels
PRISM 是一套免訓練異常檢測框架,涵蓋表格資料的 PRISM-T 和視覺資料的 PRISM-V,不需最佳化網絡權重。它在 47 個 ADBench 數據集上取得最先進的平均 AUROC,在 MVTec AD 和 VisA 上亦有具競爭力的表現,為異常檢測提供免訓練基線。
Can neural networks detect anomalies without learning?
In this paper, we introduce PRISM, a training-free anomaly detection framework for both tabular (PRISM-T) and visual (PRISM-V) data. Using only a single-layer perceptron for tabular data and a simple CNN for visual data, PRISM combines randomly initialized neural networks with statistical distance-based scoring, without optimizing network weights.
Despite its simplicity, PRISM achieves state-of-the-art mean AUROC across 47 ADBench datasets and competitive performance on MVTec AD and VisA.
These results raise a fundamental question: If untrained neural networks can already achieve such strong performance, how much does feature learning really contribute to anomaly detection?
We hope this work offers a new perspective on the role of learning in anomaly detection and establishes a strong training-free baseline for future research.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co