Ocean-going camera systems have given scientists access to amazing data products that allow them to monitor populations and discover new animals. Many groups have had success training and deploying machine learning models to help sort incoming visual data. But these models typically do not generalize well to new situations -- different cameras or illumination, new organisms appearing, changes in the appearance  of the seafloor -- an especially vexing problem in a dynamic ocean. Improving the robustness of these tools will allow marine ecologists to better leverage existing data and provide engineers with the ability to deploy instruments in ever more remote parts of the ocean. 

For this competition, we have selected data from the broader [FathomNet](https://fathomnet.org/fathomnet/#/) annotated image set that represents a challenging use-case: the training set is collected in the upper ocean (< 800 m) while the target data is collected from deeper waters. This is a common scenario in ocean research: deeper waters are more difficult to access and typically more annotated data is available closer to the surface. The species distributions are often overlapping, but not identical, and diverge as the vertical distance between the samples increases. The challenge is both to identify animals in a target image and assess if the image is from a different distribution relative to the training data. Such out-of-sample detection could help scientists discover new animals and improve ecosystem management practices.  

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F3258%2F806da28465b4f5fc843dc6d1421784cc%2Ffathomnet_image.jpg?generation=1679607795591616&alt=media)

The images for both the training and target data were collected by a single camera system deployed by the [Monterey Bay Aquarium Research Institute](https://www.mbari.org/) (MBARI) on several of its [Remotely Operated Vehicles](https://www.mbari.org/our-work/technologies/vehicles/?visc-qf-vehicle_tax_filter_technology_type%5B%5D=remotely-operated-vehicle-rov) off the coast of Central California. We encourage participants to leverage outside data sources as they see fit. Teams should plan on specifying additional data sources and/or pretrained models used when uploading results. Pretrained models can be used for initialization of training (e.g. ImageNet or COCO classification or detection models provided by many deep learning packages).

## Competition information
This competition is presented as part of the [10th Fine-Grained Visual Categorization](https://sites.google.com/view/fgvc10/home) (FGVC10) workshp at [CVPR 2023](https://cvpr.thecvf.com/Conferences/2023) in Vancouver, Canada.  

Please feel free to open an issue on the [competition git repo](https://github.com/fathomnet/fgvc-comp-2023) if you have a question, comment, or problem. We will also respond to threads opened on the competition discussion board here. 

## Acknowledgements
The images for this competition has been generously provided by [MBARI](https://www.mbari.org/). Annotations were produced by the experts in the [MBARI Video Lab](https://doi.org/10.1109/OCEANS.2006.306879).