中文
相关论文

相关论文: Robust SAM: On the Adversarial Robustness of Visio…

200 篇论文

Sharpness-Aware Minimization (SAM) is an effective method for improving generalization ability by regularizing loss sharpness. In this paper, we explore SAM in the context of adversarial robustness. We find that using only SAM can achieve…

机器学习 · 计算机科学 2023-07-04 Zeming Wei , Jingyu Zhu , Yihao Zhang

The recently introduced Segment Anything Model (SAM), a Visual Foundation Model (VFM), has demonstrated impressive capabilities in zero-shot segmentation tasks across diverse natural image datasets. Despite its success, SAM encounters…

计算机视觉与模式识别 · 计算机科学 2024-08-23 Chunpeng Zhou , Kangjie Ning , Qianqian Shen , Sheng Zhou , Zhi Yu , Haishuai Wang

The Segment Anything Model (SAM) is a deep neural network foundational model designed to perform instance segmentation which has gained significant popularity given its zero-shot segmentation ability. SAM operates by generating masks based…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Yona Falinie A. Gaus , Neelanjan Bhowmik , Brian K. S. Isaac-Medina , Toby P. Breckon

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…

计算机视觉与模式识别 · 计算机科学 2020-06-11 Muzammal Naseer , Salman Khan , Munawar Hayat , Fahad Shahbaz Khan , Fatih Porikli

Training segmentation models for medical images continues to be challenging due to the limited availability of data annotations. Segment Anything Model (SAM) is a foundation model that is intended to segment user-defined objects of interest…

计算机视觉与模式识别 · 计算机科学 2023-08-09 Maciej A. Mazurowski , Haoyu Dong , Hanxue Gu , Jichen Yang , Nicholas Konz , Yixin Zhang

Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated…

计算机视觉与模式识别 · 计算机科学 2025-03-07 Aishik Konwer , Zhijian Yang , Erhan Bas , Cao Xiao , Prateek Prasanna , Parminder Bhatia , Taha Kass-Hout

The Segment Anything Model (SAM) has revolutionized image segmentation through its innovative prompt-based approach, yet the critical role of prompt engineering in its success remains underexplored. This paper presents the first…

计算机视觉与模式识别 · 计算机科学 2025-07-15 Yidong Jiang

While the Segment Anything Model (SAM) transforms interactive segmentation with zero-shot abilities, its inherent vulnerabilities present a single-point risk, potentially leading to the failure of numerous downstream applications.…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Yi Qin , Rui Wang , Tao Huang , Tong Xiao , Liping Jing

Segment Anything Model (SAM) is an advanced foundational model for image segmentation, which is gradually being applied to remote sensing images (RSIs). Due to the domain gap between RSIs and natural images, traditional methods typically…

计算机视觉与模式识别 · 计算机科学 2025-01-14 Nanqing Liu , Xun Xu , Yongyi Su , Haojie Zhang , Heng-Chao Li

Remote sensing solutions for avalanche segmentation and mapping are key to supporting risk forecasting and mitigation in mountain regions. Synthetic Aperture Radar (SAR) imagery from Sentinel-1 can be effectively used for this task, but…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Riccardo Gelato , Carlo Sgaravatti , Jakob Grahn , Giacomo Boracchi , Filippo Maria Bianchi

The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting. Despite SAM finding applications and adaptations in various domains, its…

计算机视觉与模式识别 · 计算机科学 2025-02-14 Xumeng Han , Longhui Wei , Xuehui Yu , Zhiyang Dou , Xin He , Kuiran Wang , Yingfei Sun , Zhenjun Han , Qi Tian

The Segment Anything Model (SAM), a foundation model for general image segmentation, has demonstrated impressive zero-shot performance across numerous natural image segmentation tasks. However, SAM's performance significantly declines when…

计算机视觉与模式识别 · 计算机科学 2023-09-19 Cheng Chen , Juzheng Miao , Dufan Wu , Zhiling Yan , Sekeun Kim , Jiang Hu , Aoxiao Zhong , Zhengliang Liu , Lichao Sun , Xiang Li , Tianming Liu , Pheng-Ann Heng , Quanzheng Li

Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, yet suffers from inevitably decreased clean accuracy. Instead…

机器学习 · 计算机科学 2024-06-06 Yihao Zhang , Hangzhou He , Jingyu Zhu , Huanran Chen , Yifei Wang , Zeming Wei

The Segment Anything Model (SAM) has gained significant attention in the field of image segmentation due to its impressive capabilities and prompt-based interface. While SAM has already been extensively evaluated in various domains, its…

图像与视频处理 · 电气工程与系统科学 2023-09-01 Botond Fazekas , José Morano , Dmitrii Lachinov , Guilherme Aresta , Hrvoje Bogunović

\noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2 (SAM2) have demonstrated strong performance by refining how…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Mohamad Alansari , Muzammal Naseer , Hasan Al Marzouqi , Naoufel Werghi , Sajid Javed

The Foundation model for image segmentation, Segment Anything (SAM), has been actively researched in various fields since its proposal. Various researches have been proposed to adapt SAM to specific domains, with one notable approach…

计算机视觉与模式识别 · 计算机科学 2024-09-25 Joohyeok Kim , Joonhyeon Song , Seohwan Yun , Seongho Yoon , Sangmin Lee

Due to the inherent flexibility of prompting, foundation models have emerged as the predominant force in the fields of natural language processing and computer vision. The recent introduction of the Segment Anything Model (SAM) signifies a…

图像与视频处理 · 电气工程与系统科学 2024-01-09 Yichi Zhang , Zhenrong Shen , Rushi Jiao

Segment Anything Models (SAM) have made significant advancements in image segmentation, allowing users to segment target portions of an image with a single click (i.e., user prompt). Given its broad applications, the robustness of SAM…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Yifan Shen , Zhengyuan Li , Gang Wang

Semantic segmentation is a core task in computer vision. Existing methods are generally divided into two categories: automatic and interactive. Interactive approaches, exemplified by the Segment Anything Model (SAM), have shown promise as…

计算机视觉与模式识别 · 计算机科学 2023-12-07 Yimu Pan , Sitao Zhang , Alison D. Gernand , Jeffery A. Goldstein , James Z. Wang

Powered by massive curated training data, Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. However, the vanilla SAM is class agnostic and heavily…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Duojun Huang , Xinyu Xiong , Jie Ma , Jichang Li , Zequn Jie , Lin Ma , Guanbin Li