English
Related papers

Related papers: Detect Anything in Real Time: From Single-Prompt S…

200 papers

We present EfficientViT-SAM, a new family of accelerated segment anything models. We retain SAM's lightweight prompt encoder and mask decoder while replacing the heavy image encoder with EfficientViT. For the training, we begin with the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Zhuoyang Zhang , Han Cai , Song Han

Existing OCR engines or document image analysis systems typically rely on training separate models for text detection in varying scenarios and granularities, leading to significant computational complexity and resource demands. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Xingyu Wan , Chengquan Zhang , Pengyuan Lyu , Sen Fan , Zihan Ni , Kun Yao , Errui Ding , Jingdong Wang

In this paper, we introduce SAM3-UNet, a simplified variant of Segment Anything Model 3 (SAM3), designed to adapt SAM3 for downstream tasks at a low cost. Our SAM3-UNet consists of three components: a SAM3 image encoder, a simple adapter…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Xinyu Xiong , Zihuang Wu , Lei Lu , Yufa Xia

The Segment Anything Model (SAM) is a powerful vision foundation model that is revolutionizing the traditional paradigm of segmentation. Despite this, a reliance on prompting each frame and large computational cost limit its usage in…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Zijian Wu , Adam Schmidt , Peter Kazanzides , Septimiu E. Salcudean

Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Yuchen Guan , Chong Sun , Canmiao Fu , Zhipeng Huang , Chun Yuan , Chen Li

Vision-language segmentation models such as SAM3 enable flexible, prompt-driven visual grounding, but inherit large, general-purpose text encoders originally designed for open-ended language understanding. In practice, segmentation prompts…

Artificial Intelligence · Computer Science 2026-02-13 Chengxi Zeng , Yuxuan Jiang , Ge Gao , Shuai Wang , Duolikun Danier , Bin Zhu , Stevan Rudinac , David Bull , Fan Zhang

Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Danish Nazir , Antoine Hanna-Asaad , Lucas Görnhardt , Jan Piewek , Thorsten Bagdonat , Tim Fingscheidt

Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-01 Ao Wang , Hui Chen , Zijia Lin , Jungong Han , Guiguang Ding

Recently segment anything model (SAM) has attracted widespread concerns, and it is often treated as a vision foundation model for universal segmentation. Some researchers have attempted to directly apply the foundation model to the RGB-D…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Jia Lin , Xiaofei Zhou , Jiyuan Liu , Runmin Cong , Guodao Zhang , Zhi Liu , Jiyong Zhang

The Segment Anything Model (SAM), developed by Meta AI Research, represents a significant breakthrough in computer vision, offering a robust framework for image and video segmentation. This survey provides a comprehensive exploration of the…

Open-Vocabulary Multi-Label Recognition (OV-MLR) aims to identify multiple seen and unseen object categories within an image, requiring both precise intra-class localization to pinpoint objects and effective inter-class reasoning to model…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Haijing Liu , Tao Pu , Hefeng Wu , Keze Wang , Liang Lin

Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt (e.g., points, bounding boxes, or masks) and an input image,…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Yihao Huang , Yue Cao , Tianlin Li , Felix Juefei-Xu , Di Lin , Ivor W. Tsang , Yang Liu , Qing Guo

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

Open-vocabulary segmentation models such as SAM3 perform well across broad categories via text prompting, yet degrade when target classes are visually underrepresented in pretraining or depart from canonical depictions-limitations text…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Abderrahmene Boudiaf , Irfan Hussain , Sajid Javed

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 prompted. Interactivity is a key strength of SAMs, allowing users…

Image and Video Processing · Electrical Eng. & Systems 2024-03-18 Yiqing Shen , Jingxing Li , Xinyuan Shao , Blanca Inigo Romillo , Ankush Jindal , David Dreizin , Mathias Unberath

Few-Shot Semantic Segmentation (FSS) focuses on segmenting novel object categories from only a handful of annotated examples. Most existing approaches rely on extensive episodic training to learn transferable representations, which is both…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Yi-Jen Tsai , Yen-Yu Lin , Chien-Yao Wang

Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance. However, these methods usually adopt the standard full…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Minghui Lin , Shu Wang , Xiang Wang , Jianhua Tang , Longbin Fu , Zhengrong Zuo , Nong Sang

The recently proposed segment anything model (SAM) has made a significant influence in many computer vision tasks. It is becoming a foundation step for many high-level tasks, like image segmentation, image caption, and image editing.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Xu Zhao , Wenchao Ding , Yongqi An , Yinglong Du , Tao Yu , Min Li , Ming Tang , Jinqiao Wang

Vision transformers (ViTs) are changing the landscape of object detection approaches. A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Peixian Chen , Mengdan Zhang , Yunhang Shen , Kekai Sheng , Yuting Gao , Xing Sun , Ke Li , Chunhua Shen

We introduce a pioneering unified library that leverages depth anything, segment anything models to augment neural comprehension in language-vision model zero-shot understanding. This library synergizes the capabilities of the Depth…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Mingxiao Huo , Pengliang Ji , Haotian Lin , Junchen Liu , Yixiao Wang , Yijun Chen