Density Crop-guided Semi-supervised Object Detection in Aerial Images
Akhil Meethal, Eric Granger, Marco Pedersoli

TL;DR
This paper introduces a density crop-guided semi-supervised object detection method tailored for aerial images, improving small object detection by leveraging cluster identification during training and inference, leading to more accurate results.
Contribution
It proposes a novel density crop-guided approach that enhances semi-supervised detection of small, clustered objects in aerial images, outperforming existing methods.
Findings
Over 2% AP improvement on VisDrone and DOTA datasets.
Effective detection of small and clustered objects in aerial images.
Enhanced pseudo-label quality for small objects during training.
Abstract
One of the important bottlenecks in training modern object detectors is the need for labeled images where bounding box annotations have to be produced for each object present in the image. This bottleneck is further exacerbated in aerial images where the annotators have to label small objects often distributed in clusters on high-resolution images. In recent days, the mean-teacher approach trained with pseudo-labels and weak-strong augmentation consistency is gaining popularity for semi-supervised object detection. However, a direct adaptation of such semi-supervised detectors for aerial images where small clustered objects are often present, might not lead to optimal results. In this paper, we propose a density crop-guided semi-supervised detector that identifies the cluster of small objects during training and also exploits them to improve performance at inference. During training,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Advanced Image and Video Retrieval Techniques
