paper-with-me

홈 › Papers

Robustness of SAM: Segment Anything Under Corruptions and Beyond

2023-06-13 · Yu Qiao, Chaoning Zhang, Taegoo Kang, Donghun Kim, Chenshuang Zhang, Choong Seon Hong

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 prompts. However, there is currently a lack of comprehensive evaluation regarding its robustness under various corruptions. Understanding the robustness of SAM 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 its robustness against style transfer, which is synthetic corruption. Following by interpreting the effects of synthetic corruption as style changes, we proceed to conduct a comprehensive evaluation for its robustness against 15 types of common corruption. These corruptions mainly fall into categories such as digital, noise, weather, and blur, and within each corruption category, we explore 5 severity levels to simulate real-world corruption scenarios. Beyond the corruptions, we further assess the robustness of SAM against local occlusion and local adversarial patch attacks. 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. Given that patch attacks visible to human eyes are easily detectable, we further assess its robustness against global adversarial attacks that are imperceptible to human eyes. Overall, this work provides a comprehensive empirical study of the robustness of SAM, evaluating its performance under various corruptions and extending the assessment to critical aspects such as local occlusion, local adversarial patch attacks, and global adversarial attacks. These evaluations yield valuable insights into the practical applicability and effectiveness of SAM in addressing real-world challenges.

📄 PDF Abstract BibTeX arXiv:2306.07713

Code (0)

등록된 구현이 없습니다.

Tasks

Style Transfer

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Similar Papers 제목 키워드 기반

On the Robustness of Segment Anything

2023-05-25 · Yihao Huang, Yue Cao, Tianlin Li, Felix Juefei-Xu 외

Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt (e.g., points, bounding boxes, or masks)…

Autonomous VehiclesPrompt Learningvalid

Performance and Non-adversarial Robustness of the Segment Anything Model 2 in Surgical Video Segmentation

2024-08-07 · Yiqing Shen, Hao Ding, Xinyuan Shao, Mathias Unberath

Fully supervised deep learning (DL) models for surgical video segmentation have been shown to struggle with non-adversarial, real-world corruptions of image quality including smoke, bleeding, and low illumination. Founda…

Adversarial RobustnessImage SegmentationInteractive SegmentationNon-Adversarial Robustness+5

SARIF: Segment Anything for Robust Image Forensics

2026-06-19 · Dong-Hyun Moon, Ju-Hyeon Nam, Sang-Chul Lee arxiv

Image forgery localization remains challenging due to diverse manipulation techniques and distribution shifts. Existing forgery localization models achieve high accuracy on benchmarks but often struggle with cross-domain…

Domain Generalization

Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?

2025-05-07 · Shashank Agnihotri, David Schader, Nico Sharei, Mehmet Ege Kaçar 외

Deep learning (DL) models are widely used in real-world applications but remain vulnerable to distribution shifts, especially due to weather and lighting changes. Collecting diverse real-world data for testing the robust…

BenchmarkingSemantic Segmentation

Segment-Anything Models Achieve Zero-shot Robustness in Autonomous Driving

2024-08-19 · Jun Yan, Pengyu Wang, Danni Wang, Weiquan Huang 외

Semantic segmentation is a significant perception task in autonomous driving. It suffers from the risks of adversarial examples. In the past few years, deep learning has gradually transitioned from convolutional neural n…

Adversarial RobustnessAutonomous DrivingImage Segmentationobject-detection+3