中文
相关论文

相关论文: Taming SAM3 in the Wild: A Concept Bank for Open-V…

200 篇论文

Most existing methods for training-free open-vocabulary semantic segmentation are based on CLIP. While these approaches have made progress, they often face challenges in precise localization or require complex pipelines to combine separate…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Kaiyu Li , Shengqi Zhang , Yujie Wang , Yupeng Deng , Zhi Wang , Deyu Meng , Xiangyong Cao

SAM3 advances open-vocabulary semantic segmentation by introducing a prompt-driven mask generation paradigm. However, in multi-class open-vocabulary scenarios, masks generated independently from different category prompts lack a unified and…

计算机视觉与模式识别 · 计算机科学 2026-04-22 Yanhui Chen , Baoyao Yang , Siqi Liu , Jingchao Wang

Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentation, enabling users to segment all instances associated with a given concept using short noun-phrase (NP) prompts. While effective for…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Jingjing Li , Yue Feng , Yuchen Guo , Jincai Huang , Wei Ji , Qi Bi , Yongri Piao , Miao Zhang , Xiaoqi Zhao , Qiang Chen , Shihao Zou , Huchuan Lu , Li Cheng

Accurate lesion segmentation is essential in medical image analysis, yet most existing methods are designed for specific anatomical sites or imaging modalities, limiting their generalizability. Recent vision-language foundation models…

图像与视频处理 · 电气工程与系统科学 2026-03-30 Guoping Xu , Jayaram K. Udupa , Yubing Tong , Xin Long , Ying Zhang , Jie Deng , Weiguo Lu , You Zhang

Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference. Although modern vision-language models (VLMs) support…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Saikat Dutta , Biplab Banerjee , Hamid Rezatofighi

Reasoning Segmentation requires models to interpret complex, context-dependent linguistic queries to achieve pixel-level localization. Current dominant approaches rely heavily on Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL).…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Kai Ye , Xiaotong You , Jianghang Lin , Jiayi Ji , Pingyang Dai , Liujuan Cao

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…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Abderrahmene Boudiaf , Irfan Hussain , Sajid Javed

Change Detection (CD) is a fundamental task in remote sensing. It monitors the evolution of land cover over time. Based on this, Open-Vocabulary Change Detection (OVCD) introduces a new requirement. It aims to reduce the reliance on…

计算机视觉与模式识别 · 计算机科学 2026-04-27 Xu Zhang , Danyang Li , Yingjie Xia , Xiaohang Dong , Hualong Yu , Jianye Wang , Qicheng Li

This paper investigates the fundamental discontinuity between the latest two Segment Anything Models: SAM2 and SAM3. We explain why the expertise in prompt-based segmentation of SAM2 does not transfer to the multimodal concept-driven…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Ranjan Sapkota , Konstantinos I. Roumeliotis , Manoj Karkee

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…

计算机视觉与模式识别 · 计算机科学 2026-04-08 Yi-Jen Tsai , Yen-Yu Lin , Chien-Yao Wang

Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent works have sought to transfer knowledge embedded in vision-language models from 2D to 3D domains. However, these approaches often require prior…

计算机视觉与模式识别 · 计算机科学 2024-09-06 Hanchen Tai , Qingdong He , Jiangning Zhang , Yijie Qian , Zhenyu Zhang , Xiaobin Hu , Xiangtai Li , Yabiao Wang , Yong Liu

We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., "yellow school bus"), image exemplars,…

Is Segment Anything Model 3 (SAM3) capable in segmenting Any Pathology Images? Digital pathology segmentation spans tissue-level and nuclei-level scales, where traditional methods often suffer from high annotation costs and poor…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Qiuyu Kong , Shakiba Sharifi , Yiming Wang , Marco Cristani , Zanxi Ruan

Open-world object detection aims to localize and recognize objects beyond a fixed closed-set label space. It is commonly divided into two categories, i.e., open-vocabulary detection, which assumes a predefined category list at test time,…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Chih-Chung Liu , Zhiwei Lin , Yongtao Wang

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…

人工智能 · 计算机科学 2026-02-13 Chengxi Zeng , Yuxuan Jiang , Ge Gao , Shuai Wang , Duolikun Danier , Bin Zhu , Stevan Rudinac , David Bull , Fan Zhang

Previous work has reported that vision foundation models show promising zero-shot performance in eye image segmentation. Here we examine whether the latest iteration of the Segment Anything Model, SAM3, offers better eye image segmentation…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Diederick C. Niehorster , Marcus Nyström

Open-Vocabulary Semantic Segmentation (OVSS) has advanced with recent vision-language models (VLMs), enabling segmentation beyond predefined categories through various learning schemes. Notably, training-free methods offer scalable, easily…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Chanyoung Kim , Dayun Ju , Woojung Han , Ming-Hsuan Yang , Seong Jae Hwang

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we…

计算机视觉与模式识别 · 计算机科学 2023-03-06 Jilan Xu , Junlin Hou , Yuejie Zhang , Rui Feng , Yi Wang , Yu Qiao , Weidi Xie

Remote sensing image plays an irreplaceable role in fields such as agriculture, water resources, military, and disaster relief. Pixel-level interpretation is a critical aspect of remote sensing image applications; however, a prevalent…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Kaiyu Li , Ruixun Liu , Xiangyong Cao , Xueru Bai , Feng Zhou , Deyu Meng , Zhi Wang

Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentation remains limited…

计算机视觉与模式识别 · 计算机科学 2026-01-19 Chongcong Jiang , Tianxingjian Ding , Chuhan Song , Jiachen Tu , Ziyang Yan , Yihua Shao , Zhenyi Wang , Yuzhang Shang , Tianyu Han , Yu Tian
‹ 上一页 1 2 3 10 下一页 ›