Abstract
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Number of pages | 9 |
| Publication status | E-pub ahead of print - 2019 |
Fingerprint
Cite this
}
When a Few Clicks Make All the Difference: Improving Weakly-Supervised Wildlife Detection in UAV Images. / Kellenberger, B.A.; Marcos Gonzalez, D.; Tuia, D.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. Institute of Electrical and Electronics Engineers Inc., 2019.Research output: Chapter in Book/Report/Conference proceeding › Conference paper
TY - GEN
T1 - When a Few Clicks Make All the Difference: Improving Weakly-Supervised Wildlife Detection in UAV Images
AU - Kellenberger, B.A.
AU - Marcos Gonzalez, D.
AU - Tuia, D.
PY - 2019
Y1 - 2019
N2 - Automated object detectors on Unmanned Aerial Vehi-cles (UAVs) are increasingly employed for a wide rangeof tasks. However, to be accurate in their specific taskthey need expensive ground truth in the form of boundingboxes or positional information. Weakly-Supervised Ob-ject Detection (WSOD) overcomes this hindrance by local-izing objects with only image-level labels that are faster andcheaper to obtain, but is not on par with fully-supervisedmodels in terms of performance. In this study we proposeto combine both approaches in a model that is principallyapt for WSOD, but receives full position ground truth fora small number of images. Experiments show that withjust 1% of densely annotated images, but simple image-level counts as remaining ground truth, we effectively matchthe performance of fully-supervised models on a challeng-ing dataset with scarcely occurring wildlife on UAV imagesfrom the African savanna. As a result, with a very limitedamount of precise annotations our model can be trainedwith ground truth that is orders of magnitude cheaper andfaster to obtain while still providing the same detection per-formance.
AB - Automated object detectors on Unmanned Aerial Vehi-cles (UAVs) are increasingly employed for a wide rangeof tasks. However, to be accurate in their specific taskthey need expensive ground truth in the form of boundingboxes or positional information. Weakly-Supervised Ob-ject Detection (WSOD) overcomes this hindrance by local-izing objects with only image-level labels that are faster andcheaper to obtain, but is not on par with fully-supervisedmodels in terms of performance. In this study we proposeto combine both approaches in a model that is principallyapt for WSOD, but receives full position ground truth fora small number of images. Experiments show that withjust 1% of densely annotated images, but simple image-level counts as remaining ground truth, we effectively matchthe performance of fully-supervised models on a challeng-ing dataset with scarcely occurring wildlife on UAV imagesfrom the African savanna. As a result, with a very limitedamount of precise annotations our model can be trainedwith ground truth that is orders of magnitude cheaper andfaster to obtain while still providing the same detection per-formance.
M3 - Conference paper
BT - Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
PB - Institute of Electrical and Electronics Engineers Inc.
ER -