# Learning Spatial Fusion for Single-Shot Object Detection

arXiv: https://arxiv.org/abs/1911.09516 · HTML: https://mlsanity.com/paper/1911.09516/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2019.

## Built on by (most cited first, 30 of 59)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Track to Detect and Segment: An Online Multi-Object Tracker](https://mlsanity.com/paper/2103.08808/) (2021)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios](https://mlsanity.com/paper/2108.11539/) (2021)
- [PP-YOLOE: An evolved version of YOLO](https://mlsanity.com/paper/2203.16250/) (2022)
- [PP-YOLOv2: A Practical Object Detector](https://mlsanity.com/paper/2104.10419/) (2021)
- [Real-time Object Detection for Streaming Perception](https://mlsanity.com/paper/2203.12338/) (2022)
- [PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection](https://mlsanity.com/paper/2211.10763/) (2022)
- [AFPN: Asymptotic Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2306.15988/) (2023)
- [SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images](https://mlsanity.com/paper/2107.01548/) (2021)
- [EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network](https://mlsanity.com/paper/2105.14447/) (2021)
- [Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition](https://mlsanity.com/paper/2404.06443/) (2024)
- [PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos](https://mlsanity.com/paper/2404.08921/) (2024)
- [Gaining Scale Invariance in UAV Bird's Eye View Object Detection by Adaptive Resizing](https://mlsanity.com/paper/2101.12694/) (2021)
- [Oriented object detection in optical remote sensing images using deep learning: a survey](https://mlsanity.com/paper/2302.10473/) (2023)
- [EAutoDet: Efficient Architecture Search for Object Detection](https://mlsanity.com/paper/2203.10747/) (2022)
- [CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset](https://mlsanity.com/paper/2206.01381/) (2022)
- [Automotive Object Detection via Learning Sparse Events by Spiking Neurons](https://mlsanity.com/paper/2307.12900/) (2023)
- [Enhancing Lane Segment Perception and Topology Reasoning with Crowdsourcing Trajectory Priors](https://mlsanity.com/paper/2411.17161/) (2024)
- [Rethinking Features-Fused-Pyramid-Neck for Object Detection](https://mlsanity.com/paper/2505.12820/) (2025)
- [Weakly-Supervised Text Instance Segmentation](https://mlsanity.com/paper/2303.10848/) (2023)
- [YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification](https://mlsanity.com/paper/2305.04170/) (2023)
- [Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection](https://mlsanity.com/paper/2507.13373/) (2025)
- [TiCoSS: Tightening the Coupling between Semantic Segmentation and Stereo Matching within A Joint Learning Framework](https://mlsanity.com/paper/2407.18038/) (2024)
- [Exploring the Interactive Guidance for Unified and Effective Image Matting](https://mlsanity.com/paper/2205.08324/) (2022)
- [FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications](https://mlsanity.com/paper/2209.03157/) (2022)
- [Transformer-based stereo-aware 3D object detection from binocular images](https://mlsanity.com/paper/2304.11906/) (2023)
- [SL-YOLO: A Stronger and Lighter Drone Target Detection Model](https://mlsanity.com/paper/2411.11477/) (2024)
- [RS-YOLOX: A High Precision Detector for Object Detection in Satellite Remote Sensing Images](https://mlsanity.com/paper/2502.02850/) (2025)

## Abstract (arXiv)

Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection. However, the inconsistency across different feature scales is a primary limitation for the single-shot detectors based on feature pyramid. In this work, we propose a novel and data driven strategy for pyramidal feature fusion, referred to as adaptively spatial feature fusion (ASFF). It learns the way to spatially filter conflictive information to suppress the inconsistency, thus improving the scale-invariance of features, and introduces nearly free inference overhead. With the ASFF strategy and a solid baseline of YOLOv3, we achieve the best speed-accuracy trade-off on the MS COCO dataset, reporting 38.1% AP at 60 FPS, 42.4% AP at 45 FPS and 43.9% AP at 29 FPS. The code is available at https://github.com/ruinmessi/ASFF