Office-Home数据集

Office-Home 是一个用于域适应的基准数据集，它包含 4 个域，每个域由 65 个类别组成。这四个领域是： 艺术——素描、绘画、装饰等形式的艺术形象；剪贴画——剪贴画图像的集合；产品——没有背景的物体图像；和真实世界——用普通相机拍摄的物体图像。它包含 15,500 张图像，平均每个类大约 70 张图像，一个类最多 99 张图像。

 Artistic images (A), Clip Art ©, Product images §和Real-World images ®。

Office-Home is a benchmark dataset for domain adaptation which contains 4 domains where each domain consists of 65 categories. The four domains are: Art – artistic images in the form of sketches, paintings, ornamentation, etc.; Clipart – collection of clipart images; Product – images of objects without a background and Real-World – images of objects captured with a regular camera. It contains 15,500 images, with an average of around 70 images per class and a maximum of 99 images in a class.

GitHub is where over 94 million developers shape the future of software, together. Contribute to the open source community, manage your Git repositories, review code like a pro, track bugs and features, power your CI/CD and DevOps workflows, and secure code before you commit it.

Home

Papers With Code highlights trending Machine Learning research and the code to implement it.

Load the Office-Home Dataset for domain adaptation in Python with one line of code in seconds and plug it in TensorFlow and PyTorch with Activeloop Hub.

The Office dataset contains 31 object categories in three domains: Amazon, DSLR and Webcam. The 31 categories in the dataset consist of objects commonly encountered in office settings, such as keyboards, file cabinets, and laptops. The Amazon domain contains on average 90 images per class and 2817 images in total. As these images were captured from a website of online merchants, they are captured against clean background and at a unified scale. The DSLR domain contains 498 low-noise high resolution images (4288×2848). There are 5 objects per category. Each object was captured from different viewpoints on average 3 times. For Webcam, the 795 images of low resolution (640×480) exhibit significant noise and color as well as white balance artifacts.

本文作者：朱勇椿，中国科学院计算技术研究所博士生，研究方向为数据挖掘和迁移学习。 本期我们将为大家介绍一种极为简单的 深度子领域自适应的方法（DSAN），在大多数方法都使用很多项loss相加、越来越复杂的大环…