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

Abstract

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.

Panoptic Segmentation

“…This subset includes both datasets for which SAM outperforms and underperforms RITM according to automatic metrics. ADE20K [117] BBBC038v1 [12] Cityscapes [25] DOORS [80] DRAM [24] EgoHOS [113] GTEA [34,63] Hypersim [86] IBD [17] iShape [111] LVIS [44] NDD20 [100] NDISPark [22,23] OVIS [81] PPDLS [74] Plittersdorf [46] STREETS [91] TimberSeg [38] TrashCan [52] VISOR [28,27] WoodScape [112] PIDRay [104] ZeroWaste-f [6] Figure 8: Samples from the 23 diverse segmentation datasets used to evaluate SAM's zero-shot transfer capabilities.…”

“…-20 0 +20 +40 IoU delta at 1 center point GTEA [34,63] TrashCan [52] DRAM [24] PIDRay [104] Cityscapes [25] WoodScape [112] IBD [17] EgoHOS [113] Plittersdorf [46] VISOR [28,27] NDISPark [22,23] Hypersim [86] OVIS [81] ADE20K [117] iShape [111] ZeroWaste-f [6] STREETS [91] LVIS [44] NDD20 [100] TimberSeg [38] DOORS [80] BBBC038v1 [12] PPDLS [74] -21.4 Results. First, we look at automatic evaluation on the full suite of 23 datasets using mIoU.…”

“…8. This suite covers a range of domains including egocentric [34,28,113], microscopy [12], X-ray [104], underwater [52,100], aerial [17], simulation [86], driving [25], and painting [24] images. For efficient evaluation we subsampled datasets with more than 15k masks.…”

“…For single-point experiments, we select 7 datasets from our set of 23 datasets, since the full suite is too large for human review. We choose LVIS v0.5 [17], VISOR [28,27], DRAM [24], IBD [17], NDD20 [100], OVIS [81], and iShape [111], which provide a diverse collection of images, including scene-level, ego-centric, drawn, overhead, underwater, and synthetic imagery. Additionally, this set includes datasets both where SAM outperforms RITM with IoU metrics and vice-versa.…”

Application of deep learning to camera trap data for ecologists in planning / engineering -- Can captivity imagery train a model which generalises to the wild?

“…Although the wildcat is similar in appearance to other members of the cat family it is possible to distinguish between them using fine-grained image classification [13], [14]. The opportunity to achieve this fine-grained image classification system for Scottish wildcat is made possible by the fact wildcat are visually distinct, with light brown fur and black markings [5].…”