The ocean is one of the least-explored habitats on Earth. It is home to diverse animals, many that are either unknown to science or poorly understood. Scientists are increasingly leveraging ocean-going camera systems to monitor populations and discover new animals. This combination of dense, image-based sampling and a poorly-defined space of classes makes for a challenging computer vision problem: how do you get a machine learning model to flag animals that are new and different? For this competition, we have curated data from the broader [FathomNet](https://fathomnet.org/fathomnet/#/) image set that is emblematic of this challenging use-case. The training set contains 18 supercategories of marine animals collected along the ocean floor. The test set contains these same 18 supercategories *AND* new ones not represented in the training data. The challenge is to develop a model that can recognize the original 18 supercategories and flag unknown objects. Developing novel or general category discovery for ocean research will help scientists to rapidly find unlabeled objects in historic datasets and enable creative field campaigns to seek out new life. drawing 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. Participants should not use other image sets to train their models, however can leverage other types of outside data sources (e.g. text descriptions, etc) as they see fit. Pretrained models can be used for initialization of training (e.g. ImageNet or COCO classification or detection models provided by many deep learning packages). Teams should plan on specifying additional data sources and/or pretrained models used when uploading results. ### Competition information This competition is presented as part of the 11th Fine-Grained Visual Categorization [(FGVC11)](https://sites.google.com/view/fgvc11) workshop at [CVPR 2024](https://cvpr.thecvf.com/Conferences/2024) in Seattle, Washington. Please feel free to open an issue on the [competition git repo](https://github.com/fathomnet/fgvc-comp-2024) if you have a question, comment, or problem. We will also respond to threads openned on the competition discussion board here on Kaggle. ### Acknowledgements The images for this competition have been generously provided by [MBARI](https://www.mbari.org/). Annotations were produced by experts in the [MBARI Video Lab](https://doi.org/10.1109/OCEANS.2006.306879).