English
Related papers

Related papers: SlimSAM: 0.1% Data Makes Segment Anything Slim

200 papers

Recently, large vision model, Segment Anything Model (SAM), has revolutionized the computer vision field, especially for image segmentation. SAM presented a new promptable segmentation paradigm that exhibit its remarkable zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Chenglong Wang , Dexuan Li , Sucheng Wang , Chengxiu Zhang , Yida Wang , Yun Liu , Guang Yang

Accurate segmentation of anatomical structures in ultrasound (US) images, particularly small ones, is challenging due to noise and variability in imaging conditions (e.g., probe position, patient anatomy, tissue characteristics and…

Image and Video Processing · Electrical Eng. & Systems 2025-03-11 Danielle L. Ferreira , Ahana Gangopadhyay , Hsi-Ming Chang , Ravi Soni , Gopal Avinash

In medical imaging, precise annotation of lesions or organs is often required. However, 3D volumetric images typically consist of hundreds or thousands of slices, making the annotation process extremely time-consuming and laborious.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Bingzhi Shen , Lufan Chang , Siqi Chen , Shuxiang Guo , Hao Liu

This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less…

Computation and Language · Computer Science 2025-01-28 Xiaodong Chen , Yuxuan Hu , Jing Zhang , Yanling Wang , Cuiping Li , Hong Chen

Semantic segmentations of pathological entities have crucial clinical value in computational pathology workflows. Foundation models, such as the Segment Anything Model (SAM), have been recently proposed for universal use in segmentation…

Image and Video Processing · Electrical Eng. & Systems 2023-07-20 Jingwei Zhang , Ke Ma , Saarthak Kapse , Joel Saltz , Maria Vakalopoulou , Prateek Prasanna , Dimitris Samaras

Segment Anything Model (SAM) has gained significant attention because of its ability to segment various objects in images given a prompt. The recently developed SAM 2 has extended this ability to video inputs. This opens an opportunity to…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Haoyu Dong , Hanxue Gu , Yaqian Chen , Jichen Yang , Yuwen Chen , Maciej A. Mazurowski

The Segment Anything Model (SAM) has been a cornerstone in the field of interactive segmentation, propelling significant progress in generative AI, computational photography, and medical imaging. Despite its ability to process arbitrary…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Balakrishnan Varadarajan , Bilge Soran , Forrest Iandola , Xiaoyu Xiang , Yunyang Xiong , Lemeng Wu , Chenchen Zhu , Raghuraman Krishnamoorthi , Vikas Chandra

The recently introduced Segment Anything Model (SAM) combines a clever architecture and large quantities of training data to obtain remarkable image segmentation capabilities. However, it fails to reproduce such results for…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Tal Shaharabany , Aviad Dahan , Raja Giryes , Lior Wolf

Localizing object parts precisely is essential for tasks such as object recognition and robotic manipulation. Recent part segmentation methods require extensive training data and labor-intensive annotations. Segment-Anything Model (SAM) has…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 S. B. van Rooij , G. J. Burghouts

The Segment Anything Model (SAM) exhibits promise in generic object segmentation and offers potential for various applications. Existing methods have applied SAM to surgical instrument segmentation (SIS) by tuning SAM-based frameworks with…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Wenxi Yue , Jing Zhang , Kun Hu , Qiuxia Wu , Zongyuan Ge , Yong Xia , Jiebo Luo , Zhiyong Wang

Tooth point cloud segmentation is a fundamental task in many orthodontic applications. Current research mainly focuses on fully supervised learning which demands expensive and tedious manual point-wise annotation. Although recent…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Yifan Liu , Wuyang Li , Cheng Wang , Hui Chen , Yixuan Yuan

The Segment Anything Model (SAM), a foundation model pretrained on millions of images and segmentation masks, has significantly advanced semantic segmentation, a fundamental task in computer vision. Despite its strengths, SAM encounters two…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Li Zhang , Youwei Liang , Ruiyi Zhang , Amirhosein Javadi , Pengtao Xie

Despite the popularity of Model Compression and Multitask Learning, how to effectively compress a multitask model has been less thoroughly analyzed due to the challenging entanglement of tasks in the parameter space. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Xinglong Sun , Ali Hassani , Zhangyang Wang , Gao Huang , Humphrey Shi

The recently proposed Segment Anything Model (SAM) is a general tool for image segmentation, but it requires additional adaptation and careful fine-tuning for medical image segmentation, especially for small, irregularly-shaped, and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Yaxi Chen , Aleksandra Ivanova , Shaheer U. Saeed , Rikin Hargunani , Jie Huang , Chaozong Liu , Yipeng Hu

The subject of green AI has been gaining attention within the deep learning community given the recent trend of ever larger and more complex neural network models. Existing solutions for reducing the computational load of training at…

Machine Learning · Computer Science 2025-01-13 Xiaoying Zhi , Varun Babbar , Rundong Liu , Pheobe Sun , Fran Silavong , Ruibo Shi , Sean Moran

The Segment Anything Model (SAM) is a popular vision foundation model; however, its high computational and memory demands make deployment on resource-constrained devices challenging. While Post-Training Quantization (PTQ) is a practical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Navin Ranjan , Andreas Savakis

Leveraging the Segment Anything Model (SAM) for medical image segmentation remains challenging due to its limited adaptability across diverse medical domains. Although fine-tuned variants, such as MedSAM, improve performance in scenarios…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Jianghao Wu , Yicheng Wu , Yutong Xie , Wenjia Bai , You Zhang , Feilong Tang , Yulong Li , Imran Razzak , Daniel F Schmidt , Yasmeen George

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

Computation and Language · Computer Science 2024-12-19 Weiyu Huang , Yuezhou Hu , Guohao Jian , Jun Zhu , Jianfei Chen

Modern deep learning models are over-parameterized, where the optimization setup strongly affects the generalization performance. A key element of reliable optimization for these systems is the modification of the loss function.…

Machine Learning · Computer Science 2022-12-09 Kayhan Behdin , Qingquan Song , Aman Gupta , David Durfee , Ayan Acharya , Sathiya Keerthi , Rahul Mazumder

Diffusion models (DMs), lauded for their generative performance, are computationally prohibitive due to their billion-scale parameters and iterative denoising dynamics. Existing efficiency techniques, such as quantization, timestep…

Machine Learning · Computer Science 2026-01-21 Arani Roy , Shristi Das Biswas , Kaushik Roy