Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation

arXiv:2405.07969v1 Announce Type: new
Abstract: Zero-shot anomaly segmentation using pre-trained foundation models is a promising approach that enables effective algorithms without expensive, domain-specific training or fine-tuning. Ensuring that these methods work across various environmental conditions and are robust to distribution shifts is an open problem. We investigate the performance of WinCLIP [14] zero-shot anomaly segmentation algorithm by perturbing test data using three semantic transformations: bounded angular rotations, bounded saturation shifts, and hue shifts. We empirically measure a lower performance bound …

abstract algorithms anomaly arxiv clip cs.ai cs.cv distribution domain environmental fine-tuning foundation performance robust robustness segmentation semantic training type work zero-shot