# Extended Feature Pyramid Network for Small Object Detection

arXiv: https://arxiv.org/abs/2003.07021 · HTML: https://mlsanity.com/paper/2003.07021/

## Key facts

- Cited by 27 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 27 of 27)

- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning](https://mlsanity.com/paper/2308.09534/) (2023)
- [CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation](https://mlsanity.com/paper/2305.11481/) (2023)
- [Visible and Clear: Finding Tiny Objects in Difference Map](https://mlsanity.com/paper/2405.11276/) (2024)
- [A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion](https://mlsanity.com/paper/2109.01800/) (2021)
- [Learning Remote Sensing Object Detection with Single Point Supervision](https://mlsanity.com/paper/2305.14141/) (2023)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Pyramid Fusion Transformer for Semantic Segmentation](https://mlsanity.com/paper/2201.04019/) (2022)
- [3D Small Object Detection with Dynamic Spatial Pruning](https://mlsanity.com/paper/2305.03716/) (2023)
- [HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning](https://mlsanity.com/paper/2504.02440/) (2025)
- [Motion Informed Object Detection of Small Insects in Time-lapse Camera Recordings](https://mlsanity.com/paper/2212.00423/) (2022)
- [Deep-NFA: a Deep textita contrario Framework for Small Object Detection](https://mlsanity.com/paper/2303.01363/) (2023)
- [TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation](https://mlsanity.com/paper/2302.08047/) (2023)
- [YOLO-Drone:Airborne real-time detection of dense small objects from high-altitude perspective](https://mlsanity.com/paper/2304.06925/) (2023)
- [Deep Learning-Based Object Detection in Maritime Unmanned Aerial Vehicle Imagery: Review and Experimental Comparisons](https://mlsanity.com/paper/2311.07955/) (2023)
- [Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution](https://mlsanity.com/paper/2407.08466/) (2024)
- [Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion](https://mlsanity.com/paper/2408.02695/) (2024)
- [MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection](https://mlsanity.com/paper/2506.12697/) (2025)
- [PRNet: Original Information Is All You Have](https://mlsanity.com/paper/2510.09531/) (2025)
- [Iterative Learning for Instance Segmentation](https://mlsanity.com/paper/2202.09110/) (2022)
- [An advanced YOLOv3 method for small object detection](https://mlsanity.com/paper/2212.02809/) (2022)
- [Deformable Feature Alignment and Refinement for Moving Infrared Dim-small Target Detection](https://mlsanity.com/paper/2407.07289/) (2024)
- [CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement](https://mlsanity.com/paper/2409.20113/) (2024)
- [DPNet: Dynamic Pooling Network for Tiny Object Detection](https://mlsanity.com/paper/2505.02797/) (2025)
- [SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection](https://mlsanity.com/paper/2604.03176/) (2026)
- [UAV Video Deblurring via Motion-Aware Diffusion: A Path to Robust Target Detection](https://mlsanity.com/paper/2608.15259/) (2026)
- [RailGen: Improving Railway Intrusion Detection via Agent-Guided Small-Scale Foreign Object Generation](https://mlsanity.com/paper/2608.30727/) (2026)

## Abstract (arXiv)

Small object detection remains an unsolved challenge because it is hard to extract information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the performance of small objects. In this paper, we propose extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. Moreover, we design a foreground-background-balanced loss function to alleviate area imbalance of foreground and background. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results on small traffic-sign dataset Tsinghua-Tencent 100K and small category of general object detection dataset MS COCO.