# FathomNetCLEF2026 @ LifeCLEF & CVPR-FGVC — Data

来源：https://www.kaggle.com/competitions/fathomnet-2026/data

采集时间：2026-10-19T20:08:54Z

The dataset is derived from the [FathomNet Database](https://database.fathomnet.org/fathomnet/#/), which contains more than 400k images and 1M expert-curated bounding boxes, as of Feb 2026, across thousands of marine taxonomic, geologic, and equipment classes. The dataset is formatted to adhere to the [COCO Object Detection](https://cocodataset.org/#format-data) standard. For the challenge, participants will be provided with a training set of 6,463 images with both labeled and unlabeled positive instances. The test set, by contrast, is composed of 1,425 fully annotated images. To ensure broad accessibility, the entire dataset is less than 50 GB in size.

The FathomNet Database contains a wide spectrum of class labels. For this challenge, these labels were consolidated upstream into 32 grouped categories by our expert team for the [FathomVerse](https://www.fathomverse.game/) game, based on morphological and taxonomic considerations. The dataset includes only annotations using these 32 consolidated categories; the original FathomNet labels and the label mapping are not included. A full list of these categories can be found below.
- amphipod
- anemone
- barnacle
- benthic worm
- bivalve
- black coral
- bony fish
- brittle star
- calycophoran siphonophore
- chiton
- crab
- feather star
- hydroid
- isopod
- jelly
- larvacean
- octopus
- physonect siphonophore
- pyrosome
- sea cucumber
- sea fan
- sea pen
- sea slug
- sea snail
- sea squirt
- sea star
- shrimp
- soft coral
- sponge
- squat lobster
- stony coral
- urchin

## Data Format
The datasets are formatted to adhere to the COCO Object Detection standard. Every training image contains at least one annotation corresponding to 32 distinct categories.
We are not able to provide images as a single downloadable archive due to FathomNet Database's [Terms of Use](about:blank). Images should be downloaded using the indicated coco_url field in each of the annotation files. Participants can either use the provided download.py Python script or write their own. The download script will save one folder containing the images. The image folder contains files with names specified by the file_name field in dataset.json (typically UUID.extension format like 000b8e39-7240-49fd-9f50-713edcb28544.png). The id field is used for COCO format references between images and annotations. 
Files
dataset_train.json - the training images, annotations, and categories in COCO formatted json
dataset_test.json - the evaluation images in COCO formatted json
sample_submission.csv - a sample submission file in the correct format
download.py - python script to download imagery from FathomNet

## Files
* **`dataset_train.json`** \- the training images, annotations, and categories in COCO formatted json  
* **`dataset_test.json`** \- the evaluation images in COCO formatted json  
* **`download.py`** \- python script to download imagery from FathomNet


## Terms of Use
By downloading and using this dataset you are agreeing to FathomNet's [data use](https://www.fathomnet.org/datause) policy. In particular: The images are licensed under one of three Creative Commons licenses: [CC0](https://creativecommons.org/public-domain/cc0/#:~:text=CC0%20enables%20scientists%2C%20educators%2C%20artists,works%20for%20any%20purposes%20without), [CC-BY](https://creativecommons.org/licenses/by/4.0/deed.en), [CC-BY-NC](https://creativecommons.org/licenses/by-nc/4.0/deed.en), and [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en).  The annotations are licensed under a Creative Commons license CC0, CC-BY or CC-BY-NC. For more details please see the FathomNet Database [Terms of Use](https://www.fathomnet.org/terms).