SFN-YOLO combines local and global features via scale-aware fusion to detect multiscale poultry under obstructions and complex backgrounds, delivering 80.7% mAP at 7.2M parameters on the new M-SCOPE dataset.
The model fuses local details with global context to significantly enhance object perception amid challenges like scale variation, occlusion, and cluttered backgrounds
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SFN-YOLO: Towards Free-Range Poultry Detection via Scale-aware Fusion Networks
SFN-YOLO combines local and global features via scale-aware fusion to detect multiscale poultry under obstructions and complex backgrounds, delivering 80.7% mAP at 7.2M parameters on the new M-SCOPE dataset.