Black-box targeted adversarial attack on segment anything (sam)

S Zheng, C Zhang, X Hao - IEEE Transactions on Multimedia, 2024 - ieeexplore.ieee.org
Deep recognition models are widely vulnerable to adversarial examples, which change the
model output by adding quasi-imperceptible perturbation to the image input. Recently …

Fastsam3d: An efficient segment anything model for 3d volumetric medical images

Y Shen, J Li, X Shao, B Inigo Romillo, A **dal… - … Conference on Medical …, 2024 - Springer
Segment anything models (SAMs) are gaining attention for their zero-shot generalization
capability in segmenting objects of unseen classes and in unseen domains when properly …

Esp-medsam: Efficient self-prompting sam for universal domain-generalized medical image segmentation

Q Xu, J Li, X He, Z Liu, Z Chen, W Duan, C Li… - ar**: Research Perspectives and Challenges
JW Abe, J Ilao, G Foliente - 2024 30th International Conference …, 2024 - ieeexplore.ieee.org
The transition to sustainable agriculture necessitates a greater understanding of plants in
the field with automated plant phenoty**. Leaf segmentation is critical in this domain …

Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments

K Chen, D An, Y Huang, R Xu, Y Su, Y Ling… - arxiv preprint arxiv …, 2024 - arxiv.org
We address the task of Vision-Language Navigation in Continuous Environments (VLN-CE)
under the zero-shot setting. Zero-shot VLN-CE is particularly challenging due to the absence …

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

Y Lu, S Cao, YX Wang - arxiv preprint arxiv:2410.14633, 2024 - arxiv.org
Vision Foundation Models (VFMs) have demonstrated outstanding performance on
numerous downstream tasks. However, due to their inherent representation biases …

EdgeTAM: On-Device Track Anything Model

C Zhou, C Zhu, Y **ong, S Suri, F **ao, L Wu… - arxiv preprint arxiv …, 2025 - arxiv.org
On top of Segment Anything Model (SAM), SAM 2 further extends its capability from image to
video inputs through a memory bank mechanism and obtains a remarkable performance …

[HTML][HTML] An Efficient Group Convolution and Feature Fusion Method for Weed Detection

C Chen, Y Zang, J Jiao, D Yan, Z Fan, Z Cui, M Zhang - Agriculture, 2024 - mdpi.com
Weed detection is a crucial step in achieving intelligent weeding for vegetables. Currently,
research on vegetable weed detection technology is relatively limited, and existing detection …