BugNIST -- a Large Volumetric Dataset for Object Detection under Domain Shift
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913419772297216 |
|---|---|
| author | Jensen, Patrick Møller Dahl, Vedrana Andersen Gundlach, Carsten Engberg, Rebecca Kjer, Hans Martin Dahl, Anders Bjorholm |
| author_facet | Jensen, Patrick Møller Dahl, Vedrana Andersen Gundlach, Carsten Engberg, Rebecca Kjer, Hans Martin Dahl, Anders Bjorholm |
| contents | Domain shift significantly influences the performance of deep learning algorithms, particularly for object detection within volumetric 3D images. Annotated training data is essential for deep learning-based object detection. However, annotating densely packed objects is time-consuming and costly. Instead, we suggest training models on individually scanned objects, causing a domain shift between training and detection data. To address this challenge, we introduce the BugNIST dataset, comprising 9154 micro-CT volumes of 12 bug types and 388 volumes of tightly packed bug mixtures. This dataset is characterized by having objects with the same appearance in the source and target domains, which is uncommon for other benchmark datasets for domain shift. During training, individual bug volumes labeled by class are utilized, while testing employs mixtures with center point annotations and bug type labels. Together with the dataset, we provide a baseline detection analysis, with the aim of advancing the field of 3D object detection methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_01838 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | BugNIST -- a Large Volumetric Dataset for Object Detection under Domain Shift Jensen, Patrick Møller Dahl, Vedrana Andersen Gundlach, Carsten Engberg, Rebecca Kjer, Hans Martin Dahl, Anders Bjorholm Computer Vision and Pattern Recognition Artificial Intelligence I.2.10; I.4.6 Domain shift significantly influences the performance of deep learning algorithms, particularly for object detection within volumetric 3D images. Annotated training data is essential for deep learning-based object detection. However, annotating densely packed objects is time-consuming and costly. Instead, we suggest training models on individually scanned objects, causing a domain shift between training and detection data. To address this challenge, we introduce the BugNIST dataset, comprising 9154 micro-CT volumes of 12 bug types and 388 volumes of tightly packed bug mixtures. This dataset is characterized by having objects with the same appearance in the source and target domains, which is uncommon for other benchmark datasets for domain shift. During training, individual bug volumes labeled by class are utilized, while testing employs mixtures with center point annotations and bug type labels. Together with the dataset, we provide a baseline detection analysis, with the aim of advancing the field of 3D object detection methods. |
| title | BugNIST -- a Large Volumetric Dataset for Object Detection under Domain Shift |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.2.10; I.4.6 |
| url | https://arxiv.org/abs/2304.01838 |