保存:对视觉嵌入的自我注意力,用于零射击通用对象计数
Ahmed Zgaren1,2, Wassim Bouachir2, Nizar Bouguila1
1Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montréal, QC H3G 1M8, Canada.
Journal of imaging
|February 25, 2025
概括
本研究引入了一种自动化的零射击计数方法,超越了现有的零射击和少数射击技术. 这种新的方法提高了各种应用的视觉对象计数精度.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 人工智能的人工智能
背景情况:
- 通用视觉对象计数旨在识别和量化图像中的对象.
- 零射击计数使得在没有先例的情况下对任意类的对象计数成为可能,与需要示例的少数射击方法形成鲜明对比.
- 现有的方法通常需要示例或缺乏快速处理所需的自动化.
研究的目的:
- 提出一种完全自动化的零射击计数方法,其性能优于当前的零射击和少数射击方法.
- 为了提高视觉对象计数在各种领域的准确性和效率.
主要方法:
- 从预训练的基于检测的骨干中利用特征地图.
- 介绍一个视觉嵌入模块,以生成语义嵌入与对象上下文信息.
- 使用自我注意匹配模块来创建头计数器的编码表示.
主要成果:
- 在FSC147数据集上的零射击计数中实现了最先进的性能.
- 获得了8.89的最佳平均绝对误差 (MAE) 和35.83.83的根平均平方误差 (RMSE).
- 与几次射击方法相比,证明了具有竞争力的结果.
结论:
- 拟议的方法在自动零射击视觉对象计数方面取得了重大进展.
- 该方法在树木计数,野生动物监测和医疗图像分析 (例如,血液细胞计数) 的应用方面表现有前途.
- 这项工作突破了视觉对象计数的界限,实现了更有效,更准确的自动化解决方案.
相关概念视频
01:15Depth Perception and Spatial Vision
510
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
510
01:24Vision
52.9K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
52.9K