Localizing grouped instances for efficient detection in low-resource scenarios

A. Royer, C. Lampert, in:, IEEE Winter Conference on Applications of Computer Vision, IEEE, 2020, pp. 1716–1725.


Conference Paper | Published | English
Department
Abstract
State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life object detection applications, for example in remote sensing, instead require dealing with large images that contain only a few small objects of a single class, scattered heterogeneously across the space. In addition, they are often subject to strict computational constraints, such as limited battery capacity and computing power.To tackle these more practical scenarios, we propose a novel flexible detection scheme that efficiently adapts to variable object sizes and densities: We rely on a sequence of detection stages, each of which has the ability to predict groups of objects as well as individuals. Similar to a detection cascade, this multi-stage architecture spares computational effort by discarding large irrelevant regions of the image early during the detection process. The ability to group objects provides further computational and memory savings, as it allows working with lower image resolutions in early stages, where groups are more easily detected than individuals, as they are more salient. We report experimental results on two aerial image datasets, and show that the proposed method is as accurate yet computationally more efficient than standard single-shot detectors, consistently across three different backbone architectures.
Publishing Year
Date Published
2020-03-01
Proceedings Title
IEEE Winter Conference on Applications of Computer Vision
Article Number
1716-1725
Conference
WACV: Winter Conference on Applications of Computer Vision
Conference Location
Snowmass Village, CO, United States
Conference Date
2020-03-01 – 2020-03-05
IST-REx-ID

Cite this

Royer A, Lampert C. Localizing grouped instances for efficient detection in low-resource scenarios. In: IEEE Winter Conference on Applications of Computer Vision. IEEE; 2020:1716-1725. doi:10.1109/WACV45572.2020.9093288
Royer, A., & Lampert, C. (2020). Localizing grouped instances for efficient detection in low-resource scenarios. In IEEE Winter Conference on Applications of Computer Vision (pp. 1716–1725). Snowmass Village, CO, United States: IEEE. https://doi.org/10.1109/WACV45572.2020.9093288
Royer, Amélie, and Christoph Lampert. “Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios.” In IEEE Winter Conference on Applications of Computer Vision, 1716–25. IEEE, 2020. https://doi.org/10.1109/WACV45572.2020.9093288.
A. Royer and C. Lampert, “Localizing grouped instances for efficient detection in low-resource scenarios,” in IEEE Winter Conference on Applications of Computer Vision, Snowmass Village, CO, United States, 2020, pp. 1716–1725.
Royer A, Lampert C. 2020. Localizing grouped instances for efficient detection in low-resource scenarios. IEEE Winter Conference on Applications of Computer Vision. WACV: Winter Conference on Applications of Computer Vision 1716–1725.
Royer, Amélie, and Christoph Lampert. “Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios.” IEEE Winter Conference on Applications of Computer Vision, IEEE, 2020, pp. 1716–25, doi:10.1109/WACV45572.2020.9093288.

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data IST Research Explorer

Sources

arXiv 2004.12623

Search this title in

Google Scholar
ISBN Search