Eastern Canada Flocks: Images and manually annotated bird positions
Bibliographic record
Abstract
The Eastern Canada (ECA) Flocks data set consists of manually annotated Images from the Common Eider (COEI, Somateria mollissima) Winter Survey and the Greater Snow Geese (GSGO, Anser caerulescens atlanticus) Spring Survey. The images were taken in Eastern Canada using fixed-wing aircraft and manually annotated with ImageJ’s Cell counter plugins. We selected and annotated the ECA Flocks images in order to test the precision of the CountEm flock size estimation method. ECA Flocks includes 179 COEI and 99 GSGO single flock images. We cut each image manually to a rectangle that excluded large parts of the image with no birds. Both versions (original and cut) of each image are available in the data set. We manually annotated 637,555 (124,309 COEI and 514,235 GSGO) bird positions in the cut images from both surveys. Each bird has an associated “Type” which refers to species and/or sex. Sex identification was only possible for adult common eiders since females and immature males are brown birds whereas adult males have mainly white plumage. 64,484 male and 58,029 females were identified in the COEI images, as well as 1796 birds of other species. 504,891 Snow Geese and 9344 birds of other species were labeled in the GSGO images. A .csv file including all annotated bird positions and types is available for each image. The COEI and GSGO photos of the ECA Flocks data set were taken in the years 2006 and 2018 and 2016-2018 respectively. We selected these photos in order to include images with different quality and resolution. COEI and GSGO flock sizes range from 6 to 4,154 and from 43 to 36, 241 respectively. There is high variability in light conditions, backgrounds, number and spatial arrangement of birds across the images. The data set is therefore potentially useful to test the precision of methods for analyzing imagery to estimate the abundance of animals by directly detecting, identifying and counting individuals.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.016 | 0.011 |
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 source (direct Gemma or distilled Codex), 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".