Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection
Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects. In this paper, we propose a convex-hull feature adaptation (CFA) approach for configuring convolutional features in accordance with oriented and densely packed object layouts. CFA is rooted in convex-hull feature representation, which defines a set of dynamically predicted feature points guided by the convex intersection over union (CIoU) to bound the extent of objects. CFA pursues optimal feature assignment by constructing convex-hull sets and dynamically splitting positive or negative convex-hulls. By simultaneously considering overlapping convex-hulls and objects and penalizing convex-hulls shared by multiple objects, CFA alleviates spatial feature aliasing towards optimal feature adaptation. Experiments on DOTA and SKU110K-R datasets show that CFA significantly outperforms the baseline approach, achieving new state-of-the-art detection performance.
PDF AbstractCode
DOTA
SKU110K-R
Results from the Paper
Ranked #34 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Object Detection In Aerial Images | DOTA | CFA | mAP | 76.67% | # 34 |
