YOLO-FireAD uses attention guided inverted residuals and fused max average pooling to reach 34.6% mAP50-95 with 1.45M parameters, about 1.8 points above YOLOv8n on one fire dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
YOLO-FireAD: Efficient Fire Detection via Attention-Guided Inverted Residual Learning and Dual-Pooling Feature Preservation
YOLO-FireAD uses attention guided inverted residuals and fused max average pooling to reach 34.6% mAP50-95 with 1.45M parameters, about 1.8 points above YOLOv8n on one fire dataset.