FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement

ArXi:2603.19608v1 Announce Type: cross Fine-grained anomaly detection is crucial in industrial and medical applications, but labeled anomalies are often scarce, making zero-shot detection challenging. While vision-language models like CLIP offer promising solutions, they struggle with foreground-background feature entanglement and coarse textual semantics. We propose FB-CLIP, a framework that enhances anomaly localization via multi-strategy textual representations and foreground-background separation.