Toggle Main Menu Toggle Search

Open Access padlockePrints

NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation

Lookup NU author(s): Dr Cameron Trotter, Georgia Atkinson, Dr Matthew Sharpe, Kirsten Crane, Dr Stephen McGough, Professor Nick Wright, Dr Ben Burville, Professor Per Berggren


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


We introduce the Northumberland Dolphin Dataset 2020 (NDD20), a challenging image dataset annotated for both coarse and fine-grained instance segmentation and categorisation. This dataset, the first release of the NDD (13), was created in response to the rapid expansion of computer vision into conservation research and the production of fielddeployable systems suited to extreme environmental conditions - an area with few open source datasets. NDD20 contains a large collection of above and below water images of two different dolphin species for traditional coarse and fine-grained segmentation. All data contained in NDD20 was obtained via manual collection in the North Sea around the Northumberland coastline, UK. We present experimentation using standard deep learning network architecture trained using NDD20 and report baselines results.

Publication metadata

Author(s): Trotter C, Atkinson G, Sharpe M, Richardson K, McGough S, Wright N, Burville B, Berggren P

Publication type: Article

Publication status: Published

Journal: arXiv

Year: 2020

Pages: 5

Online publication date: 27/05/2020

Acceptance date: 27/05/2020

Publisher: arXiv


Notes: NDD20 was released at this year’s FGVC7 Workshop as a part of CVPR2020. Our accompanying paper can be accessed at, with the dataset itself available at