中文
相关论文

相关论文: SAM3-Assisted Training of Lightweight YOLO Models …

200 篇论文

Deep learning has advanced two fundamentally different paradigms for instance segmentation: specialized models optimized through task-specific fine-tuning and generalist foundation models capable of zero-shot segmentation. This work…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Ranjan Sapkota , Konstantinos I. Roumeliotis , Manoj Karkee , Nikolaos D. Tselikas

Currently, deep learning-based instance segmentation for various applications (e.g., Agriculture) is predominantly performed using a labor-intensive process involving extensive field data collection using sophisticated sensors, followed by…

计算机视觉与模式识别 · 计算机科学 2025-03-03 Ranjan Sapkota , Achyut Paudel , Manoj Karkee

Foundation-model pipelines for individual-level livestock monitoring -- combining open-vocabulary detection, promptable video segmentation, and self-supervised visual embeddings -- have raised the accuracy ceiling of precision livestock…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Haiyu Yang , Miel Hostens

Foundation models (FM) are reshaping computer vision by reducing reliance on task-specific supervised learning and leveraging general visual representations learned at scale. In precision livestock farming, most pipelines remain dominated…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Ye Bi , Bimala Acharya , David Rosero , Juan Steibel

In precision crop protection, (target-orientated) object detection in image processing can help navigate Unmanned Aerial Vehicles (UAV, crop protection drones) to the right place to apply the pesticide. Unnecessary application of non-target…

计算机视觉与模式识别 · 计算机科学 2021-03-09 Zhenwang Qin , Wensheng Wang , Karl-Heinz Dammer , Leifeng Guo , Zhen Cao

The Segment Anything Model 3 (SAM3) advances visual understanding with Promptable Concept Segmentation (PCS) across images and videos, but its unified architecture (shared vision backbone, DETR-style detector, dense-memory tracker) remains…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Chengxi Zeng , Yuxuan Jiang , Aaron Zhang

The rapid growth of artificial intelligence in poultry farming has highlighted the challenge of efficiently labeling large, diverse datasets. Manual annotation is time-consuming and costly, making it impractical for modern systems that…

This study addresses the demand for real-time detection of tomatoes and tomato flowers by agricultural robots deployed on edge devices in greenhouse environments. Under practical imaging conditions, object detection systems often face…

图像与视频处理 · 电气工程与系统科学 2026-02-02 Hung-Chih Tu , Bo-Syun Chen , Yun-Chien Cheng

With the development of large language models, many remarkable linguistic systems like ChatGPT have thrived and achieved astonishing success on many tasks, showing the incredible power of foundation models. In the spirit of unleashing the…

计算机视觉与模式识别 · 计算机科学 2024-01-30 Dingyuan Zhang , Dingkang Liang , Hongcheng Yang , Zhikang Zou , Xiaoqing Ye , Zhe Liu , Xiang Bai

The Segment Anything Model (SAM) enables promptable, high-quality segmentation but is often too computationally expensive for latency-critical settings. TinySAM is a lightweight, distilled SAM variant that preserves strong zero-shot mask…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Kenneth Xu , Songhan Wu

Training deep models with limited annotations poses a significant challenge when applied to diverse practical domains. Employing semi-supervised learning alongside the self-supervised model offers the potential to enhance label efficiency.…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Ziting Wen , Oscar Pizarro , Stefan Williams

In this study, we propose an automated framework for camel farm monitoring, introducing two key contributions: the Unified Auto-Annotation framework and the Fine-Tune Distillation framework. The Unified Auto-Annotation approach combines two…

计算机视觉与模式识别 · 计算机科学 2024-02-13 Raza Imam , Muhammad Huzaifa , Nabil Mansour , Shaher Bano Mirza , Fouad Lamghari

We introduce Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM). This integration enables the detection and segmentation of any regions based on arbitrary text inputs and…

计算机视觉与模式识别 · 计算机科学 2024-01-26 Tianhe Ren , Shilong Liu , Ailing Zeng , Jing Lin , Kunchang Li , He Cao , Jiayu Chen , Xinyu Huang , Yukang Chen , Feng Yan , Zhaoyang Zeng , Hao Zhang , Feng Li , Jie Yang , Hongyang Li , Qing Jiang , Lei Zhang

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,…

In the Detection and Multi-Object Tracking of Sweet Peppers Challenge, we present Track Any Peppers (TAP) - a weakly supervised ensemble technique for sweet peppers tracking. TAP leverages the zero-shot detection capabilities of…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Jia Syuen Lim , Yadan Luo , Zhi Chen , Tianqi Wei , Scott Chapman , Zi Huang

Foundation models, especially vision-language models (VLMs), offer compelling zero-shot object detection for applications like autonomous driving, a domain where manual labelling is prohibitively expensive. However, their detection latency…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Uday Bhaskar , Rishabh Bhattacharya , Avinash Patel , Sarthak Khoche , Praveen Anil Kulkarni , Naresh Manwani

The Segment Anything Model (SAM) is a recently proposed prompt-based segmentation model in a generic zero-shot segmentation approach. With the zero-shot segmentation capacity, SAM achieved impressive flexibility and precision on various…

计算机视觉与模式识别 · 计算机科学 2023-08-30 Can Cui , Ruining Deng , Quan Liu , Tianyuan Yao , Shunxing Bao , Lucas W. Remedios , Yucheng Tang , Yuankai Huo

Monitoring leftover products provides valuable insights that can be used to optimize future production. This is especially important for German bakeries because freshly baked goods have a very short shelf life. Automating this process can…

计算机视觉与模式识别 · 计算机科学 2026-02-11 Thomas H. Schmitt , Maximilian Bundscherer , Tobias Bocklet

Automated wildlife surveys based on drone imagery and object detection technology are a powerful and increasingly popular tool in conservation biology. Most detectors require training images with annotated bounding boxes, which are tedious,…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Giacomo May , Emanuele Dalsasso , Benjamin Kellenberger , Devis Tuia

Recent breakthroughs in large foundation models have enabled the possibility of transferring knowledge pre-trained on vast datasets to domains with limited data availability. Agriculture is one of the domains that lacks sufficient data.…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Yanan Wang , Zhenghao Fei , Ruichen Li , Yibin Ying
‹ 上一页 1 2 3 10 下一页 ›