A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qin, Meng'en, Song, Yu, Zhao, Quanling, Yang, Xiaodong, Che, Yingtao, Yang, Xiaohui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909045340766208
author Qin, Meng'en
Song, Yu
Zhao, Quanling
Yang, Xiaodong
Che, Yingtao
Yang, Xiaohui
author_facet Qin, Meng'en
Song, Yu
Zhao, Quanling
Yang, Xiaodong
Che, Yingtao
Yang, Xiaohui
contents Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit them from capturing discriminative features and recognizing small objects. In this work, we propose Asymptotic Content-Aware Pyramid Attention Network (A3-FPN), to augment multi-scale feature representation via the asymptotically disentangled framework and content-aware attention modules. Specifically, A3-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 A3-FPN can be easily integrated into state-of-the-art CNN and Transformer-based architectures, yielding remarkable performance gains. Notably, when paired with OneFormer and Swin-L backbone, A3-FPN achieves 49.6 mask AP on MS COCO and 85.6 mIoU on Cityscapes. Codes are available at https://github.com/mason-ching/A3-FPN.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10210
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
Qin, Meng'en
Song, Yu
Zhao, Quanling
Yang, Xiaodong
Che, Yingtao
Yang, Xiaohui
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit them from capturing discriminative features and recognizing small objects. In this work, we propose Asymptotic Content-Aware Pyramid Attention Network (A3-FPN), to augment multi-scale feature representation via the asymptotically disentangled framework and content-aware attention modules. Specifically, A3-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 A3-FPN can be easily integrated into state-of-the-art CNN and Transformer-based architectures, yielding remarkable performance gains. Notably, when paired with OneFormer and Swin-L backbone, A3-FPN achieves 49.6 mask AP on MS COCO and 85.6 mIoU on Cityscapes. Codes are available at https://github.com/mason-ching/A3-FPN.
title A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.10210