# HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection

arXiv: https://arxiv.org/abs/1904.11141 · HTML: https://mlsanity.com/paper/1904.11141/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2019.

## Built on by (most cited first, 3 of 3)

- [Changes to Captions: An Attentive Network for Remote Sensing Change Captioning](https://mlsanity.com/paper/2304.01091/) (2023)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Multi-level feature fusion network combining attention mechanisms for polyp segmentation](https://mlsanity.com/paper/2309.10219/) (2023)

## Abstract (arXiv)

Object detection has been a challenging task in computer vision. Although significant progress has been made in object detection with deep neural networks, the attention mechanism is far from development. In this paper, we propose the hybrid attention mechanism for single-stage object detection. First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection. In particular, stacked dilated convolution layers with symmetrically fixed rates are constructed to learn spatial attention. The channel attention is proposed with the cross-level group normalization and squeeze-and-excitation module. Aligned attention is constructed with organized deformable filters. Second, the three kinds of attention are unified to construct the hybrid attention mechanism. We then embed the hybrid attention into Retina-Net and propose the efficient single-stage HAR-Net for object detection. The attention modules and the proposed HAR-Net are evaluated on the COCO detection dataset. Experiments demonstrate that hybrid attention can significantly improve the detection accuracy and the HAR-Net can achieve the state-of-the-art 45.8% mAP, outperform existing single-stage object detectors.