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

Cameron Trotter, Georgia Atkinson, Matt Sharpe, Kirsten Crane, Stephen McGough, Nick Wright, Ben Burville, Per Berggren

Abstract:

We introduce the Northumberland Dolphin Dataset 2020
(NDD20), a challenging image dataset annotated for both
coarse and fine-grained instance segmentation and cate-
gorisation. 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 field-
deployable systems suited to extreme environmental con-
ditions - 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 experimen-
tation using standard deep learning network architecture
trained using NDD20 and report baselines results.