Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance of a prompt. However, there is currently a lack of comprehensive evaluation regarding its robustness under various corruptions. Understanding SAM's robustness across different corruption scenarios is crucial for its real-world deployment. Prior works show that SAM is biased towards texture (style) rather than shape, motivated by which we start by investigating SAM's robustness against style transfer, which is synthetic corruption. Following the interpretation of the corruption's effect as style change, we proceed to conduct a comprehensive evaluation of the SAM for its robustness against 15 types of common corruption. These corruptions mainly fall into categories such as digital, noise, weather, and blur. Within each of these corruption categories, we explore 5 severity levels to simulate real-world corruption scenarios. Beyond the corruptions, we further assess its robustness regarding local occlusion and local adversarial patch attacks in images. To the best of our knowledge, our work is the first of its kind to evaluate the robustness of SAM under style change, local occlusion, and local adversarial patch attacks. Considering that patch attacks visible to human eyes are easily detectable, we also assess SAM's robustness against adversarial perturbations that are imperceptible to human eyes. Overall, this work provides a comprehensive empirical study on SAM's robustness, evaluating its performance under various corruptions and extending the assessment to critical aspects like local occlusion, local patch attacks, and imperceptible adversarial perturbations, which yields valuable insights into SAM's practical applicability and effectiveness in addressing real-world challenges.

翻译：暂无翻译