# AugFPN: Improving Multi-scale Feature Learning for Object Detection

arXiv: https://arxiv.org/abs/1912.05384 · HTML: https://mlsanity.com/paper/1912.05384/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2019.

## Built on by (most cited first, 30 of 55)

- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [Feature Aggregation and Propagation Network for Camouflaged Object Detection](https://mlsanity.com/paper/2212.00990/) (2022)
- [DRCT: Saving Image Super-resolution away from Information Bottleneck](https://mlsanity.com/paper/2404.00722/) (2024)
- [UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery](https://mlsanity.com/paper/2112.10415/) (2021)
- [LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network](https://mlsanity.com/paper/2404.01614/) (2024)
- [GraphFPN: Graph Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2108.00580/) (2021)
- [Dogfight: Detecting Drones from Drones Videos](https://mlsanity.com/paper/2103.17242/) (2021)
- [AFPN: Asymptotic Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2306.15988/) (2023)
- [New Insights for the Stability-Plasticity Dilemma in Online Continual Learning](https://mlsanity.com/paper/2302.08741/) (2023)
- [A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation](https://mlsanity.com/paper/2105.03186/) (2021)
- [Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2111.11057/) (2021)
- [AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes](https://mlsanity.com/paper/2106.10409/) (2021)
- [Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images](https://mlsanity.com/paper/2407.19696/) (2024)
- [Hierarchical Attention Fusion for Geo-Localization](https://mlsanity.com/paper/2102.09186/) (2021)
- [CE-FPN: Enhancing Channel Information for Object Detection](https://mlsanity.com/paper/2103.10643/) (2021)
- [Rebalanced Zero-shot Learning](https://mlsanity.com/paper/2210.07031/) (2022)
- [PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN](https://mlsanity.com/paper/2103.15428/) (2021)
- [BoxMask: Revisiting Bounding Box Supervision for Video Object Detection](https://mlsanity.com/paper/2210.06008/) (2022)
- [DSLA: Dynamic smooth label assignment for efficient anchor-free object detection](https://mlsanity.com/paper/2208.00817/) (2022)
- [DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention](https://mlsanity.com/paper/2209.13933/) (2022)
- [Multi-Scale Contrastive Learning for Video Temporal Grounding](https://mlsanity.com/paper/2412.07157/) (2024)
- [RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection](https://mlsanity.com/paper/2110.12130/) (2021)
- [What Are Expected Queries in End-to-End Object Detection?](https://mlsanity.com/paper/2206.01232/) (2022)
- [MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domain](https://mlsanity.com/paper/2304.07724/) (2023)
- [Revisiting the Loss Weight Adjustment in Object Detection](https://mlsanity.com/paper/2103.09488/) (2021)
- [Dynamic Multi-Scale Loss Optimization for Object Detection](https://mlsanity.com/paper/2108.04014/) (2021)
- [S2-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2206.07298/) (2022)
- [Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes](https://mlsanity.com/paper/2303.14628/) (2023)
- [Few-Shot Learning in Video and 3D Object Detection: A Survey](https://mlsanity.com/paper/2507.17079/) (2025)
- [Learning to Reduce Information Bottleneck for Object Detection in Aerial Images](https://mlsanity.com/paper/2204.02033/) (2022)

## Abstract (arXiv)

Current state-of-the-art detectors typically exploit feature pyramid to detect objects at different scales. Among them, FPN is one of the representative works that build a feature pyramid by multi-scale features summation. However, the design defects behind prevent the multi-scale features from being fully exploited. In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems. Specifically, AugFPN consists of three components: Consistent Supervision, Residual Feature Augmentation, and Soft RoI Selection. AugFPN narrows the semantic gaps between features of different scales before feature fusion through Consistent Supervision. In feature fusion, ratio-invariant context information is extracted by Residual Feature Augmentation to reduce the information loss of feature map at the highest pyramid level. Finally, Soft RoI Selection is employed to learn a better RoI feature adaptively after feature fusion. By replacing FPN with AugFPN in Faster R-CNN, our models achieve 2.3 and 1.6 points higher Average Precision (AP) when using ResNet50 and MobileNet-v2 as backbone respectively. Furthermore, AugFPN improves RetinaNet by 1.6 points AP and FCOS by 0.9 points AP when using ResNet50 as backbone. Codes will be made available.