# Individual common dolphin identification via metric embedding learning

arXiv: https://arxiv.org/abs/1901.03662 · HTML: https://mlsanity.com/paper/1901.03662/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2019.

## Built on by (most cited first, 9 of 9)

- [Perspectives on individual animal identification from biology and computer vision](https://mlsanity.com/paper/2103.00560/) (2021)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification](https://mlsanity.com/paper/2410.06977/) (2024)
- [An Individual Identity-Driven Framework for Animal Re-Identification](https://mlsanity.com/paper/2410.22927/) (2024)
- [Membership Inference Attack for Beluga Whales Discrimination](https://mlsanity.com/paper/2302.14769/) (2023)
- [Recurrence over Video Frames (RoVF) for the Re-identification of Meerkats](https://mlsanity.com/paper/2406.13002/) (2024)
- [Siamese Networks for Cat Re-Identification: Exploring Neural Models for Cat Instance Recognition](https://mlsanity.com/paper/2501.02112/) (2025)
- [Towards Automatic Cetacean Photo-Identification: A Framework for Fine-Grain, Few-Shot Learning in Marine Ecology](https://mlsanity.com/paper/2212.03646/) (2022)
- [Categorical Keypoint Positional Embedding for Robust Animal Re-Identification](https://mlsanity.com/paper/2412.00818/) (2024)

## Abstract (arXiv)

Photo-identification (photo-id) of dolphin individuals is a commonly used technique in ecological sciences to monitor state and health of individuals, as well as to study the social structure and distribution of a population. Traditional photo-id involves a laborious manual process of matching each dolphin fin photograph captured in the field to a catalogue of known individuals. We examine this problem in the context of open-set recognition and utilise a triplet loss function to learn a compact representation of fin images in a Euclidean embedding, where the Euclidean distance metric represents fin similarity. We show that this compact representation can be successfully learnt from a fairly small (in deep learning context) training set and still generalise well to out-of-sample identities (completely new dolphin individuals), with top-1 and top-5 test set (37 individuals) accuracy of 90.5±2 and 93.6±1 percent. In the presence of 1200 distractors, top-1 accuracy dropped by 12%; however, top-5 accuracy saw only a 2.8% drop