English
Related papers

Related papers: Fast SAM2 with Text-Driven Token Pruning

200 papers

The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among various prompt types (such as points, boxes, texts, and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Xiaoqi Wang , Clint Sebastian , Wenbin He , Liu Ren

The recent Segment Anything Model (SAM) 2 has demonstrated remarkable foundational competence in semantic segmentation, with its memory mechanism and mask decoder further addressing challenges in video tracking and object occlusion, thereby…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Jieming Yu , An Wang , Wenzhen Dong , Mengya Xu , Mobarakol Islam , Jie Wang , Long Bai , Hongliang Ren

Video Object Segmentation and Tracking (VOST) presents a complex yet critical challenge in computer vision, requiring robust integration of segmentation and tracking across temporally dynamic frames. Traditional methods have struggled with…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Guoping Xu , Jayaram K. Udupa , Yajun Yu , Hua-Chieh Shao , Songlin Zhao , Wei Liu , You Zhang

Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Shayan Jalilian , Abdul Bais

Segment Anything Model 2 (SAM2) demonstrated impressive zero-shot capabilities on natural images but faces challenges in biomedical segmentation due to significant domain shifts and prompt dependency. To address these limitations, we…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Hinako Mitsuoka , Kazuhiro Hotta

Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Aishik Konwer , Zhijian Yang , Erhan Bas , Cao Xiao , Prateek Prasanna , Parminder Bhatia , Taha Kass-Hout

Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable encoder to further enhance performance remains an open…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Xinyu Xiong , Zihuang Wu , Lei Zhang , Lei Lu , Ming Li , Guanbin Li

Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks and has become the state-of-the-art for visual object tracking. The model stores information from previous frames in a memory bank, enabling…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Alen Adamyan , Tomáš Čížek , Matej Straka , Klara Janouskova , Martin Schmid

Video camouflaged object segmentation (VCOS), aiming at segmenting camouflaged objects that seamlessly blend into their environment, is a fundamental vision task with various real-world applications. With the release of SAM2, video…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yuli Zhou , Yawei Li , Yuqian Fu , Luca Benini , Ender Konukoglu , Guolei Sun

\noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2 (SAM2) have demonstrated strong performance by refining how…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Mohamad Alansari , Muzammal Naseer , Hasan Al Marzouqi , Naoufel Werghi , Sajid Javed

Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering, image captioning and so on, but their inference cost remains a significant challenge due to the large number…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Weichen Zhang , Zhui Zhu , Ningbo Li , Shilong Tao , Kebin Liu , Yunhao Liu

Segment Anything Model 2 (SAM 2), a prompt-driven foundation model extending SAM to both image and video domains, has shown superior zero-shot performance compared to its predecessor. Building on SAM's success in medical image segmentation,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-06 Bin Xie , Hao Tang , Yan Yan , Gady Agam

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…

Computer Vision and Pattern Recognition · Computer Science 2024-03-08 Tao Zhou , Wenhan Luo , Qi Ye , Zhiguo Shi , Jiming Chen

The semantic segmentation task in pathology plays an indispensable role in assisting physicians in determining the condition of tissue lesions. With the proposal of Segment Anything Model (SAM), more and more foundation models have seen…

Image and Video Processing · Electrical Eng. & Systems 2024-09-05 Mingya Zhang , Liang Wang , Zhihao Chen , Yiyuan Ge , Xianping Tao

Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process. Recent advancements in foundation models for video object segmentation,…

Image and Video Processing · Electrical Eng. & Systems 2025-11-04 Yuwen Chen , Zafer Yildiz , Qihang Li , Yaqian Chen , Haoyu Dong , Hanxue Gu , Nicholas Konz , Maciej A. Mazurowski

Fully supervised deep learning (DL) models for surgical video segmentation have been shown to struggle with non-adversarial, real-world corruptions of image quality including smoke, bleeding, and low illumination. Foundation models for…

Image and Video Processing · Electrical Eng. & Systems 2024-08-19 Yiqing Shen , Hao Ding , Xinyuan Shao , Mathias Unberath

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xinqi Jin , Hanxun Yu , Bohan Yu , Kebin Liu , Jian Liu , Keda Tao , Yixuan Pei , Huan Wang , Fan Dang , Jiangchuan Liu , Weiqiang Wang

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Yifei Liu , Mathias Gehrig , Nico Messikommer , Marco Cannici , Davide Scaramuzza

Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results. However, adapting MLLM to segmentation is computationally…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Xiaobo Yang , Xiaojin Gong

Semantic Segmentation combines two sub-tasks: the identification of pixel-level image masks and the application of semantic labels to those masks. Recently, so-called Foundation Models have been introduced; general models trained on very…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 David Balaban , Justin Medich , Pranay Gosar , Justin Hart