[HTML][HTML] Digital twins as a unifying framework for surgical data science: the enabling role of geometric scene understanding

H Ding, L Seenivasan, BD Killeen, SM Cho… - Artificial Intelligence …, 2024 - oaepublish.com
Surgical data science is devoted to enhancing the quality, safety, and efficacy of
interventional healthcare. While the use of powerful machine learning algorithms is …

Parameter efficient fine-tuning via cross block orchestration for segment anything model

Z Peng, Z Xu, Z Zeng, L Xie, Q Tian… - Proceedings of the …, 2024 - openaccess.thecvf.com
Parameter-efficient fine-tuning (PEFT) is an effective methodology to unleash the potential of
large foundation models in novel scenarios with limited training data. In the computer vision …

ASAM: Boosting Segment Anything Model with Adversarial Tuning

B Li, H Xiao, L Tang - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
In the evolving landscape of computer vision foundation models have emerged as pivotal
tools exhibiting exceptional adaptability to a myriad of tasks. Among these the Segment …

Kind: Knowledge integration and diversion in diffusion models

Y Xie, F Feng, J Wang, X Geng, Y Rui - arXiv preprint arXiv:2408.07337, 2024 - arxiv.org
Pre-trained models have become the preferred backbone due to the expansion of model
parameters, with techniques like Parameter-Efficient Fine-Tuning (PEFTs) typically fixing the …

Multi-scale contrastive adaptor learning for segmenting anything in underperformed scenes

K Zhou, Z Qiu, D Fu - Neurocomputing, 2024 - Elsevier
Foundational vision models, such as the Segment Anything Model (SAM), have achieved
significant breakthroughs through extensive pre-training on large-scale visual datasets …

GeoSAM: Fine-tuning SAM with sparse and dense visual prompting for automated segmentation of mobility infrastructure

RI Sultan, C Li, H Zhu, P Khanduri, M Brocanelli… - arXiv preprint arXiv …, 2023 - arxiv.org
The Segment Anything Model (SAM) has shown impressive performance when applied to
natural image segmentation. However, it struggles with geographical images like aerial and …

BF-SAM: enhancing SAM through multi-modal fusion for fine-grained building function identification

Z Gong, B Li, C Wang, J Chen… - International Journal of …, 2024 - Taylor & Francis
Building function identification (BFI) is crucial for urban planning and governance. The
traditional remote sensing approach primarily focuses on extracting the physical features of …

A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem

K Ding, Y Wang, G Meng, S Xiang - arXiv preprint arXiv:2410.11686, 2024 - arxiv.org
The advent of pre-trained vision-language foundation models has revolutionized the field of
zero/few-shot (ie, low-shot) image recognition. The key challenge to address under the …

Sam-octa: Prompting segment-anything for octa image segmentation

X Chen, C Wang, H Ning, S Li, M Shen - arXiv preprint arXiv:2310.07183, 2023 - arxiv.org
Segmenting specific targets or biomarkers is necessary to analyze optical coherence
tomography angiography (OCTA) images. Previous methods typically segment all the …

FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models

Y Xie, F Feng, R Shi, J Wang, X Geng - arXiv preprint arXiv:2409.19289, 2024 - arxiv.org
Diffusion models often face slow convergence, and existing efficient training techniques,
such as Parameter-Efficient Fine-Tuning (PEFT), are primarily designed for fine-tuning pre …