English
Related papers

Related papers: Task-Aware Low-Rank Adaptation of Segment Anything…

200 papers

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 Anything Model (SAM) by Meta AI has distinguished itself in…

Computer Vision and Pattern Recognition · Computer Science 2024-05-02 Bo Li , Haoke Xiao , Lv Tang

We present a novel Speech Augmented Language Model (SALM) with {\em multitask} and {\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech…

Computation and Language · Computer Science 2023-10-17 Zhehuai Chen , He Huang , Andrei Andrusenko , Oleksii Hrinchuk , Krishna C. Puvvada , Jason Li , Subhankar Ghosh , Jagadeesh Balam , Boris Ginsburg

We present the Recognize Anything Model (RAM): a strong foundation model for image tagging. RAM makes a substantial step for large models in computer vision, demonstrating the zero-shot ability to recognize any common category with high…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Youcai Zhang , Xinyu Huang , Jinyu Ma , Zhaoyang Li , Zhaochuan Luo , Yanchun Xie , Yuzhuo Qin , Tong Luo , Yaqian Li , Shilong Liu , Yandong Guo , Lei Zhang

The Segment Anything Model (SAM) marks a notable milestone in segmentation models, highlighted by its robust zero-shot capabilities and ability to handle diverse prompts. SAM follows a pipeline that separates interactive segmentation into…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 You Huang , Zongyu Lan , Liujuan Cao , Xianming Lin , Shengchuan Zhang , Guannan Jiang , Rongrong Ji

The rapid advancement of foundation modelslarge-scale neural networks trained on diverse, extensive datasetshas revolutionized artificial intelligence, enabling unprecedented advancements across domains such as natural language processing,…

Large Multimodal Models (LMMs) have shown significant progress in various complex vision tasks with the solid linguistic and reasoning capacity inherited from large language models (LMMs). Low-rank adaptation (LoRA) offers a promising…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Liang Mi , Weijun Wang , Wenming Tu , Qingfeng He , Rui Kong , Xinyu Fang , Yazhu Dong , Yikang Zhang , Yunchun Li , Meng Li , Haipeng Dai , Guihai Chen , Yunxin Liu

The Segment Anything Model (SAM) has demonstrated significant potential in medical image segmentation. Yet, its performance is limited when only a small amount of labeled data is available, while there is abundant valuable yet often…

Image and Video Processing · Electrical Eng. & Systems 2025-11-13 Shuhang Chen , Hangjie Yuan , Pengwei Liu , Hanxue Gu , Tao Feng , Dong Ni

Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation data across various medical imaging modalities and equipment,…

Image and Video Processing · Electrical Eng. & Systems 2024-07-12 Hairong Shi , Songhao Han , Shaofei Huang , Yue Liao , Guanbin Li , Xiangxing Kong , Hua Zhu , Xiaomu Wang , Si Liu

This paper presents the Autonomous Driving Segment Anything Model (AD-SAM), a fine-tuned vision foundation model for semantic segmentation in autonomous driving (AD). AD-SAM extends the Segment Anything Model (SAM) with a dual-encoder and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Mario Camarena , Het Patel , Fatemeh Nazari , Evangelos Papalexakis , Mohamadhossein Noruzoliaee , Jia Chen

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…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Nanqing Liu , Xun Xu , Yongyi Su , Haojie Zhang , Heng-Chao Li

The recently released Segment Anything Model (SAM) has shown powerful zero-shot segmentation capabilities through a semi-automatic annotation setup in which the user can provide a prompt in the form of clicks or bounding boxes. There is…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Benjamin Towle , Xin Chen , Ke Zhou

Recent advancements in biomedical image analysis have been significantly driven by the Segment Anything Model (SAM). This transformative technology, originally developed for general-purpose computer vision, has found rapid application in…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Ho Hin Lee , Yu Gu , Theodore Zhao , Yanbo Xu , Jianwei Yang , Naoto Usuyama , Cliff Wong , Mu Wei , Bennett A. Landman , Yuankai Huo , Alberto Santamaria-Pang , Hoifung Poon

Road crack segmentation is critical for robotic systems tasked with the inspection, maintenance, and monitoring of road infrastructures. Existing deep learning-based methods for crack segmentation are typically trained on specific datasets,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Xiaoyan Jiang , Xinlong Wan , Kaiying Zhu , Xihe Qiu , Zhijun Fang

In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle's surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Junbao Zhou , Jilin Mei , Pengze Wu , Liang Chen , Fangzhou Zhao , Xijun Zhao , Yu Hu

Low-rank adaptation (LoRA) assigns a uniform rank to every adapted weight matrix - a practical convenience that ignores a fundamental reality: different layers contribute unequally to task adaptation. We address this with a lightweight…

Machine Learning · Computer Science 2026-05-19 Ramakrishnan Sathyavageeswaran

Medical image segmentation often faces the challenge of prohibitively expensive annotation costs. While few-shot learning offers a promising solution to alleviate this burden, conventional approaches still rely heavily on pre-training with…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Jie Xu , Xiaokang Li , Chengyu Yue , Yuanyuan Wang , Yi Guo

The emerging scale segmentation model, Segment Anything (SAM), exhibits impressive capabilities in zero-shot segmentation for natural images. However, when applied to medical images, SAM suffers from noticeable performance drop. To make SAM…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Xinrong Hu , Xiaowei Xu , Yiyu Shi

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Guanyao Wu , Haoyu Liu , Hongming Fu , Yichuan Peng , Jinyuan Liu , Xin Fan , Risheng Liu

The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Lei Ke , Mingqiao Ye , Martin Danelljan , Yifan Liu , Yu-Wing Tai , Chi-Keung Tang , Fisher Yu

The Segment Anything Model 2 (SAM2) has emerged as a foundation model for universal segmentation. Owing to its generalizable visual representations, SAM2 has been successfully applied to various downstream tasks. However, extending SAM2 to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Jiyuan Liu , Jia Lin , Xiaofei Zhou , Runmin Cong , Deyang Liu , Zhi Liu