Annotated Underwater Images of Round Goby (Neogobius melanostomus) in the Great Lakes from 2020-2023 to Support Deep Learning and Fisheries Assessment
Bibliographic record
Abstract
This dataset contains more than 37,000 high-resolution images of natural lake bottom habitats containing round goby (Neogobius melanostomus) captured by autonomous underwater vehicles (AUVs). Round goby are invasive to the Laurentian Great Lakes, but are an important prey item for economically valuable predators, and thus of interest to managers. Individual round goby within each image were manually traced to create binary masks and JSON files to support training and validation of deep learning algorithms to automatically detect round goby. The data were collected in Lakes Michigan, Huron, and Ontario between June to September, 2020, 2021, 2022, and 2023 using two different camera systems integrated into L3Harris-OceanServer Iver3 AUVs. Each image is attributed with information about its latitude, longitude, depth, altitude, and other values recorded by the AUVs’ on-board sensors and recorded in a metadata file (RoundGoby_Dataset_Metadata.csv). To ensure the quality and accuracy of the data, the manual labels were inspected by three independent observers to verify their correctness, ensuring that no non-fish objects were mistakenly labeled as fish, and to exclude fish that were not round goby, background substrates, mussels, and fish-like objects. The data are organized into zip files, each corresponding to different collection months, years, and camera systems. Zip files contain (i) raw RGB images, (ii) ground truth binary masks, (iii) JSON files with polygon coordinates, (iv) bounding box coordinates in pixels, and (v) bounding box coordinates in YOLO format to support algorithm development. Collectively, this dataset provides a comprehensive resource for automating the detection and sizing of round goby in color images.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".