# Google Universal Image Embedding — Data

来源：https://www.kaggle.com/competitions/google-universal-image-embedding/data

采集时间：2026-10-24T13:22:49Z

In this competition, you are asked to develop models that can efficiently retrieve images from a large database. For each query image, the model is expected to retrieve the most similar images from an index set.

We do not provide a training set. In accordance with the [rules](https://www.kaggle.com/competitions/google-universal-image-embedding/rules), any training data may be used, as long as it is disclosed in the forum by the relevant deadline. There exist many public datasets for different object types (e.g., artworks, landmarks, products, etc), and we encourage participants to experiment with them as needed.

<!--- 
The query images are listed in the `test/` folder, while the "index" images from which you are retrieving are listed in `index/`. Each image has a unique `id`. Since there are a large number of images, each image is placed within three subfolders according to the first three characters of the image `id` (i.e. image `abcdef.jpg` is placed in `a/b/c/abcdef.jpg`).
-->

Our evaluation dataset, which is kept private, contains images of the following types of object: apparel & accessories, packaged goods, landmarks, furniture & home decor, storefronts, dishes, artwork, toys, memes, illustrations and cars. The header image above shows examples of images in these domains, which are similar to the ones in the evaluation set. Labels are defined generally at the instance level, for example: the same T-shirt, the same building, the same painting, the same dish.

The following plot shows the distribution of object types in the dataset:

![](assets/9a691f56028b99d3dbd4bb09.png)

<!--- 
The provided `index/` and `test/` images in the publicly available dataset are provided to mock the size and structure of the private data, but are otherwise not directly used.
-->

Please see the [Evaluation](https://www.kaggle.com/competitions/google-universal-image-embedding/overview/evaluation) page for details on how the model should be formatted and submitted.