| --- |
| license: apache-2.0 |
| language: |
| - en |
| datasets: |
| - bitmind/MS-COCO |
| - Voxel51/VisDrone2019-DET |
| - huggan/cityscapes |
| - yizhangdev/pascal-voc |
| --- |
| A<sup>3</sup>-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction |
| --------------------- |
|
|
| This repository is the checkpoints for our paper "[A<sup>3</sup>-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction](https://doi.org/10.48550/arXiv.2604.10210)". |
| A<sup>3</sup>-FPN employs a horizontally-spread column network that enables asymptotically global feature interaction and disentangles each level from all hierarchical representations. |
| In feature fusion, it collects supplementary content from the adjacent level to generate position-wise offsets and weights for context-aware resampling, and learns deep context reweights to improve intra-category similarity. |
| In feature reassembly, it further strengthens intra-scale discriminative feature learning and reassembles redundant features based on information content and spatial variation of feature maps. |
| Extensive experiments on MS COCO, VisDrone2019-DET and Cityscapes demonstrate that A<sup>3</sup>-FPN can be easily integrated into state-of-the-art CNN and Transformer-based architectures, yielding remarkable performance gains. |
|
|
| If you find A<sup>3</sup>-FPN useful in your research, please consider citing: |
| ``` |
| @article{qin2026a3, |
| title={A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction}, |
| author={Qin, Meng'en and Song, Yu and Zhao, Quanling and Yang, Xiaodong and Che, Yingtao and Yang, Xiaohui}, |
| journal={arXiv preprint arXiv:2604.10210}, |
| year={2026} |
| } |
| ``` |
