Participants are tasked with developing object detection systems that can operate effectively in a positive-unlabeled learning regime, identifying both the presence and location of marine organisms across diverse habitats. The evaluation metric is the mean Average Precision (mAP), applied to a fully labeled evaluation set. For more information on mAP see [here](https://learnopencv.com/mean-average-precision-map-object-detection-model-evaluation-metric/). The evaluation notebook can be found [here](https://www.kaggle.com/code/lauravchrobak/map50-95). To succeed, participants are expected to explore approaches that leverage unlabeled positives, including positive-unlabeled learning, semi-supervised, and self-supervised techniques. The challenge not only serves to benchmark approaches in positive-unlabeled detection but also aims to produce practical methods that can generalize to large-scale, heterogeneous marine datasets, directly supporting ongoing conservation and ecological research.

## Submission Format
Submission format should resemble the following:

| annotation_id | image_id | category_id | bbox_x | bbox_y | bbox_width | bbox_height | score |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | 1 | 28 | 476.0 | 790.0 | 77.0 | 149.0 | 0.3 |


Submissions must be provided as a CSV file where each row corresponds to a single predicted object detection. The file must contain the following columns: annotation_id, image_id, category_id, bbox_x, bbox_y, bbox_width, bbox_height, score.

The annotation_id is a unique (but otherwise arbitrary) identifier for each prediction and is used only as a row index. The image_id must exactly match the image_id of the corresponding image in the COCO-formatted test set. The category_id must match the category IDs used in both the training and test datasets.
Bounding boxes are specified using the COCO object detection format: bbox_x and bbox_y give the pixel coordinates of the top-left corner of the box, while bbox_width and bbox_height specify the width and height of the box in pixels.
The score column represents the model’s confidence for the predicted detection. Scores must be floating-point values between 0 and 1 (inclusive). Predictions may be provided in any order.