Count Anything 模型可基于文本提示计数图像中物体

New AI model called "Count Anything" does exactly what it says, and that's harder than it sounds

精选理由

计数准确率翻倍

AI 摘要

Count Anything 是首个能通过文本提示计数任意图像中物体的 AI 模型,在对比测试中将错误率降低 50%。该模型可处理从人群到显微镜下细胞样本等场景,但在极度密集物体和模糊术语上仍有困难。

AI 翻译 · 中文

Count Anything 是首个能通过文本提示计数任意图像中物体的 AI 模型,在对比测试中将错误率降低 50%。该模型可处理从人群到显微镜下细胞样本等场景,但在极度密集物体和模糊术语上仍有困难。

Decoder"Count Anything" is intended to be the first AI model capable of counting objects in any type of image, from crowds to cell samples under a microscope, using nothing more than a text prompt. In a comparative test, it cut