Search Results for author:
Found 5 papers, 2 papers with code
Object Detection in Aerial Images in Scarce Data Regimes
We demonstrate this with an in-depth analysis of existing FSOD methods on aerial images and observed a large performance gap compared to natural images.
Rethinking Intersection Over Union for Small Object Detection in Few-Shot Regime
SIoU improves small object detection in the non-few-shot regime, but this setting is unrealistic in the industry as annotated detection datasets are often too expensive to acquire.
A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Images
Finally, we develop a novel multiscale alignment method, Cross-Scales Query-Support Alignment (XQSA) for FSOD, to improve the detection of small objects.
A Unified Framework for Attention-Based Few-Shot Object Detection
In particular, for attention-based FSOD methods, it is laborious to compare the impact of the different attention mechanisms on performance.
Experience feedback using Representation Learning for Few-Shot Object Detection on Aerial Images
This training strategy encourages the network to adapt to new classes as it would at test time.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
