In the second part of a series of articles about the history of artificial intelligence, we look at important published papers in the history of AI and the concept introduced in them.
In this paper, we cover the basics of projects. We describe the different types of projects, how to create new projects from existing ones, how to import and export projects, how to use tags and descriptions, and provide some best practices.
Training a highly accurate computer vision model requires many carefully annotated images. Data gathering and annotation take time and might often prove to be hard. As the saying goes, nothing is particularly hard if you divide it into small jobs (and assign it to a team of people). This chapter details the teamwork tools implemented on the AIEX deep learning platform. An overview of organizations, projects, workgroups, and some of the best practices will be outlined in this paper.
This article reviews famous datasets in the field of computer vision.
Google has come up with a framework for data collection inspired by software development concepts in a 5-step cyclical process. In this article, we will examine google’s proposed data collection framework.
In this article, we discuss the Attention mechanism and trace its history of use from natural language processing to computer vision. And finally, we will examine transformers and their application in computer vision.
A timely and accurate diagnosis of the proximal femur and pelvis injuries in trauma patients is essential to saving their lives. High-quality clinical trauma care and treatment require both physician experience and radiography images. A multiscale deep learning algorithm called PelviXNet has been developed to rapidly and accurately detect most kinds of pelvic and hip fractures.
Nowadays with the help of computer vision technology and image processing we can classify broken and normal bone X-ray images with high accuracy. In this article, we will discuss the Deep Learning approach for this purpose.
Choosing the right images for training, validating, and testing computer vision algorithms will significantly affect your AI project’s success. To train an AI model for object detection, segmentation, and classification with human-like performance, each image in the dataset must be labeled thoughtfully and accurately. This article examines dataset annotation and labeling techniques.
To train a model or use transfer learning in machine vision, there must be enough data. Data Augmentation is a very important step that helps us increase our training data. The purpose of this article is to examine this feature and to review the techniques used to increase data on the AIEX platform.