Similarity Learning Networks for Animal Individual Re-Identification --\n Beyond the Capabilities of a Human Observer
Bibliographic record
Abstract
Deep learning has become the standard methodology to approach computer vision\ntasks when large amounts of labeled data are available. One area where\ntraditional deep learning approaches fail to perform is one-shot learning tasks\nwhere a model must correctly classify a new category after seeing only one\nexample. One such domain is animal re-identification, an application of\ncomputer vision which can be used globally as a method to automate species\npopulation estimates from camera trap images. Our work demonstrates both the\napplication of similarity comparison networks to animal re-identification, as\nwell as the capabilities of deep convolutional neural networks to generalize\nacross domains. Few studies have considered animal re-identification methods\nacross species. Here, we compare two similarity comparison methodologies:\nSiamese and Triplet-Loss, based on the AlexNet, VGG-19, DenseNet201,\nMobileNetV2, and InceptionV3 architectures considering mean average precision\n(mAP)@1 and mAP@5. We consider five data sets corresponding to five different\nspecies: humans, chimpanzees, humpback whales, fruit flies, and Siberian\ntigers, each with their own unique set of challenges. We demonstrate that\nTriplet Loss outperformed its Siamese counterpart for all species. Without any\nspecies-specific modifications, our results demonstrate that similarity\ncomparison networks can reach a performance level beyond that of humans for the\ntask of animal re-identification. The ability for researchers to re-identify an\nanimal individual upon re-encounter is fundamental for addressing a broad range\nof questions in the study of population dynamics and community/behavioural\necology. Our expectation is that similarity comparison networks are the\nbeginning of a major trend that could stand to revolutionize animal\nre-identification from camera trap data.\n
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".