Related papers: Segment (Almost) Nothing: Prompt-Agnostic Adversar…
Segment Anything Model (SAM) has gained significant recognition in the field of semantic segmentation due to its versatile capabilities and impressive performance. Despite its success, SAM faces two primary limitations: (1) it relies…
Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…
Recent advances in promptable segmentation, such as the Segment Anything Model (SAM), have enabled flexible, high-quality mask generation across a wide range of visual domains. However, SAM and similar models remain fundamentally…
Deep learning models, which are increasingly being used in the field of medical image analysis, come with a major security risk, namely, their vulnerability to adversarial examples. Adversarial examples are carefully crafted samples that…
Whole-body PET/CT is a cornerstone of oncological imaging, yet accurate lesion segmentation remains challenging due to tracer heterogeneity, physiological uptake, and multi-center variability. While fully automated methods have advanced…
Recently, promptable segmentation models, such as the Segment Anything Model (SAM), have demonstrated robust zero-shot generalization capabilities on static images. These promptable models exhibit denoising abilities for imprecise prompt…
Large, fine-grained image segmentation datasets, annotated at pixel-level, are difficult to obtain, particularly in medical imaging, where annotations also require expert knowledge. Weakly-supervised learning can train models by relying on…
The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…
Segment Anything Model (SAM), a prompt-driven foundation model for natural image segmentation, has demonstrated impressive zero-shot performance. However, SAM does not work when directly applied to medical image segmentation, since SAM…
With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, \ie, adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the…
Video object segmentation has been applied to various computer vision tasks, such as video editing, autonomous driving, and human-robot interaction. However, the methods based on deep neural networks are vulnerable to adversarial examples,…
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…
Deep learning approaches based on convolutional neural networks (CNNs) have been successful in solving a number of problems in medical imaging, including image segmentation. In recent years, it has been shown that CNNs are vulnerable to…
It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image classification. In this paper, we extend adversarial examples…
The Segment Anything Model (SAM) made an eye-catching debut recently and inspired many researchers to explore its potential and limitation in terms of zero-shot generalization capability. As the first promptable foundation model for…
Segmentation is a fundamental vision task underlying numerous downstream applications. Recent promptable segmentation models, such as Segment Anything Model 3 (SAM3), extend segmentation from category-agnostic mask prediction to…
Large foundation models, known for their strong zero-shot generalization, have excelled in visual and language applications. However, applying them to medical image segmentation, a domain with diverse imaging types and target labels,…
We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is needed to generate attacks for segmentation. In this context,…
Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this…
Adversarial training has been shown to produce state of the art results for generative image modeling. In this paper we propose an adversarial training approach to train semantic segmentation models. We train a convolutional semantic…