Abstract
This paper proposes any-scale object detection using arbitrary-scale super-resolution for continuously rescaling object images, while general multi-scale object detection uses discretely rescaled appearance representations. However, a naive usage of super-resolution produces many false-positive detections if many super-resolution images are independently fed into an object detector. Our method suppresses these false positives by predicting scale proposal maps, each of which represents a set of pixels appropriate for each super-resolution scale.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Akita, K., & Ukita, N. (2026). Any-scale Object Detection using Arbitrary-scaled Images. https://omanscience.com/en/articles/any-scale-object-detection-using-arbitrary-scaled-images
MLA 9
Akita, Kazutoshi, and Norimichi Ukita. "Any-scale Object Detection using Arbitrary-scaled Images." https://omanscience.com/en/articles/any-scale-object-detection-using-arbitrary-scaled-images.
Chicago (author–date)
Akita, Kazutoshi, and Norimichi Ukita. 2026. "Any-scale Object Detection using Arbitrary-scaled Images." https://omanscience.com/en/articles/any-scale-object-detection-using-arbitrary-scaled-images.
Harvard
Akita, K. and Ukita, N. (2026) 'Any-scale Object Detection using Arbitrary-scaled Images', Available at: https://omanscience.com/en/articles/any-scale-object-detection-using-arbitrary-scaled-images.
Vancouver
Akita K, Ukita N. Any-scale Object Detection using Arbitrary-scaled Images. https://omanscience.com/en/articles/any-scale-object-detection-using-arbitrary-scaled-images
IEEE
K. Akita, and N. Ukita, "Any-scale Object Detection using Arbitrary-scaled Images," https://omanscience.com/en/articles/any-scale-object-detection-using-arbitrary-scaled-images.