CVDec 18, 2024

HA-RDet: Hybrid Anchor Rotation Detector for Oriented Object Detection

arXiv:2412.14379v25 citationsh-index: 12025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Originality Incremental advance
AI Analysis

This addresses the problem of efficient and accurate detection of variably oriented objects in aerial imagery for computer vision applications, representing an incremental improvement over existing methods.

The paper tackles the challenge of oriented object detection in aerial images by proposing HA-RDet, a hybrid anchor-based and anchor-free detector that achieves competitive accuracies of 75.41 mAP on DOTA-v1, 65.3 mAP on DIOR-R, and 90.2 mAP on HRSC2016 while reducing computational resources.

Oriented object detection in aerial images poses a significant challenge due to their varying sizes and orientations. Current state-of-the-art detectors typically rely on either two-stage or one-stage approaches, often employing Anchor-based strategies, which can result in computationally expensive operations due to the redundant number of generated anchors during training. In contrast, Anchor-free mechanisms offer faster processing but suffer from a reduction in the number of training samples, potentially impacting detection accuracy. To address these limitations, we propose the Hybrid-Anchor Rotation Detector (HA-RDet), which combines the advantages of both anchor-based and anchor-free schemes for oriented object detection. By utilizing only one preset anchor for each location on the feature maps and refining these anchors with our Orientation-Aware Convolution technique, HA-RDet achieves competitive accuracies, including 75.41 mAP on DOTA-v1, 65.3 mAP on DIOR-R, and 90.2 mAP on HRSC2016, against current anchor-based state-of-the-art methods, while significantly reducing computational resources.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes