# Learning Spatial Fusion for Single-Shot Object Detection Source: [Learning Spatial Fusion for Single-Shot Object Detection]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:14:44.534Z Authors: Songtao Liu, Di Huang, Yunhong Wang Published: 2019-11-21T15:05:28.000Z ## Abstract 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 ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on MS COCO (test-dev)](): Object Detection; MS COCO (test-dev); mAP@.5: 64.1. - [Object Detection on COCO v2017 (test-dev)](): Object Detection; COCO v2017 (test-dev); mAP: 43.9. - [Object Detection on COCO (test-dev)](): Object Detection; COCO (test-dev); mAP: 43.9. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()