CLIP-FSQAE: Clip-Guided Finite Scalar Quantized Autoencoder for Few-Shot Anomaly Detection

Industrial anomaly detection is hindered by data inefficiency and dependence on large-scale training sets. We introduce CLIP-FSQAE, a novel framework for few-shot anomaly detection that integrates Finite Scalar Quantization (FSQ) into a CLIP-guided autoencoder. By leveraging CLIP’s vision-language alignment and image-to-text tuning, the model mitigates shortcut learning and reconstructs defective inputs using only a few normal samples. A diffusion-based synthetic anomaly generator further improves robustness and diversity. Evaluations on MVTecAD and VisA show that CLIP-FSQAE achieves state-of-the-art image- and pixel-level performance. It matches or exceeds full-data baselines with fewer than four training samples, establishing a new benchmark for few-shot industrial anomaly detection.