# AFPN: Asymptotic Feature Pyramid Network for Object Detection

arXiv: https://arxiv.org/abs/2306.15988 · HTML: https://mlsanity.com/paper/2306.15988/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 28 Jun 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution](https://mlsanity.com/paper/2006.02334/) (2020)
- [CARAFE: Content-Aware ReAssembly of FEatures](https://mlsanity.com/paper/1905.02188/) (2019)
- [Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training](https://mlsanity.com/paper/2004.06002/) (2020)
- [Rethinking Classification and Localization for Object Detection](https://mlsanity.com/paper/1904.06493/) (2019)
- [Feature Pyramid Transformer](https://mlsanity.com/paper/2007.09451/) (2020)
- [Learning Spatial Fusion for Single-Shot Object Detection](https://mlsanity.com/paper/1911.09516/) (2019)
- [AugFPN: Improving Multi-scale Feature Learning for Object Detection](https://mlsanity.com/paper/1912.05384/) (2019)
- [GraphFPN: Graph Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2108.00580/) (2021)
- [Centralized Feature Pyramid for Object Detection](https://mlsanity.com/paper/2210.02093/) (2022)
- [Dual Refinement Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/2012.01733/) (2020)

## Built on by (most cited first, 17 of 17)

- [Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism](https://mlsanity.com/paper/2309.11331/) (2023)
- [Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images](https://mlsanity.com/paper/2407.19696/) (2024)
- [BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature Fusion for Brain Tumor Detection](https://mlsanity.com/paper/2309.12585/) (2023)
- [MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection](https://mlsanity.com/paper/2502.04656/) (2025)
- [LSM-YOLO: A Compact and Effective ROI Detector for Medical Detection](https://mlsanity.com/paper/2408.14087/) (2024)
- [A Simple Detector with Frame Dynamics is a Strong Tracker](https://mlsanity.com/paper/2505.04917/) (2025)
- [MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View](https://mlsanity.com/paper/2504.18136/) (2025)
- [Multi-scale direction-aware SAR object detection network via global information fusion](https://mlsanity.com/paper/2312.16943/) (2023)
- [SaRPFF: A Self-Attention with Register-based Pyramid Feature Fusion module for enhanced RLD detection](https://mlsanity.com/paper/2402.16291/) (2024)
- [Fused attention mechanism-based ore sorting network](https://mlsanity.com/paper/2405.02785/) (2024)
- [BAFPN: Bi directional alignment of features to improve localization accuracy](https://mlsanity.com/paper/2412.01859/) (2024)
- [RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images](https://mlsanity.com/paper/2507.13120/) (2025)
- [SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detection](https://mlsanity.com/paper/2507.20188/) (2025)
- [MO R-CNN: Multispectral Oriented R-CNN for Object Detection in Remote Sensing Image](https://mlsanity.com/paper/2509.16957/) (2025)
- [CollabOD: Collaborative Multi-Backbone with Cross-scale Vision for UAV Small Object Detection](https://mlsanity.com/paper/2603.05905/) (2026)
- [FRFDet: Efficient UAV Small Object Detection with Symmetric Sampling and Scalable Fusion](https://mlsanity.com/paper/2607.04125/) (2026)
- [Weave Mamba Fusion: Global Cross-Scale Interaction for Lightweight Face Detection](https://mlsanity.com/paper/2610.05865/) (2026)

## Abstract (arXiv)

Multi-scale features are of great importance in encoding objects with scale variance in object detection tasks. A common strategy for multi-scale feature extraction is adopting the classic top-down and bottom-up feature pyramid networks. However, these approaches suffer from the loss or degradation of feature information, impairing the fusion effect of non-adjacent levels. This paper proposes an asymptotic feature pyramid network (AFPN) to support direct interaction at non-adjacent levels. AFPN is initiated by fusing two adjacent low-level features and asymptotically incorporates higher-level features into the fusion process. In this way, the larger semantic gap between non-adjacent levels can be avoided. Given the potential for multi-object information conflicts to arise during feature fusion at each spatial location, adaptive spatial fusion operation is further utilized to mitigate these inconsistencies. We incorporate the proposed AFPN into both two-stage and one-stage object detection frameworks and evaluate with the MS-COCO 2017 validation and test datasets. Experimental evaluation shows that our method achieves more competitive results than other state-of-the-art feature pyramid networks. The code is available at hrefhttps://github.com/gyyang23/AFPNhttps://github.com/gyyang23/AFPN.