Future Blog Post
Published:
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Published:
Page not found. Your pixels are in another canvas.
About me
About me
This is a page not in th emain menu
Published:
损失函数对不同的框进行不同的处理,最佳框与所有其他框之间的区分机制是 YOLO 损失的核心。使用单独的对象置信度损失 objectness 来处理分数确实比将类概率 confidence 视为分数表现得更好,在SSD目标检测中考虑类概率作为置信度分数其效果要明显差于带置信度的Yolo模型。
Published:
Lightly Insights:可以轻松获取关于机器学习数据集基本洞察的工具,可以可视化图像数据集的基本统计信息,仅需提供一个包含图像和对象检测标签的文件夹,它会生成一个包含指标和图表的静态 HTML 网页。
Published:
Meta 的两个大型模型在当前 AI 开源界处于领先地位:LLM 的 LLaMA 和 CV 的 SAM。其中Segment Anything Model 是一个基于 Transformer(ViT 主干)的视觉分割基础模型。它可以通过零样本概括自动分割任何图像。另外模型还融入了Prompt:它们可以是要分割的区域上的点、要分割的对象周围的边界框或有关应分割的内容的文本提示。该模型由 3 个组件组成:图像编码器、提示编码器和掩模解码器。
Published:
为了解决小目标检测问题,同时也可以解决超大分辨率图像的问题(如遥感图像、病理图像、医疗影像等),本文提出了一个在微调和推理阶段基于切片的通用框架。将输入图像划分为重叠的切片,对于小目标相对于输入网络的图像产生相对较大的像素区域。
Published:
YOLOv8由广受欢迎的YOLOv3和YOLOv5模型的作者 Ultralytics 开发,凭借其无锚设计将目标检测提升到了一个新的水平。YOLOv8 专为实际部署而设计,重点关注速度、延迟和经济性。
Published:
Short description of portfolio item number 1
Short description of portfolio item number 2
Published in Journal 1, 2009
This paper is about the number 1. The number 2 is left for future work.
Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1). http://academicpages.github.io/files/paper1.pdf
Published in Journal 1, 2010
This paper is about the number 2. The number 3 is left for future work.
Recommended citation: Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2). http://academicpages.github.io/files/paper2.pdf
Published in Journal 1, 2015
This paper is about the number 3. The number 4 is left for future work.
Recommended citation: Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3). http://academicpages.github.io/files/paper3.pdf
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Classification, MLT, Projects, 2023
从大模型来回溯目标分类任务,高阶题目深度分析。
Segmentation, SAM, CV, 2023
从SAM来回溯目标分割任务,高阶题目深度分析
大模型, Attention, Transformer, 2023
从视觉注意力机制到大模型Transformer架构,探索高频问题与深度解析。
Model, Loss, Optimzer, 2023
深度学习模型构建最重要的损失函数与优化器部分,本文列举在企业面试中高频问题,在此基础上结合项目实战经验给予深度解析。
Detection, Anchor-Free, Anchor-Base, 2023
本博客面向深度学习算法中常见的视觉检测任务,甄选百道常见面试题来进行深度解析,Mark.AI希望通过这些题目的整理和解析,能够为求职者提供一个系统、全面的面试准备资源,帮助你们在面试中表现出色,取得成功。该博客持续更新真实面试题,关注不迷路。