MHAF-YOLO reaches 48.9% AP on COCO with 7.1M parameters by combining auxiliary shallow-deep fusion paths and heterogeneous reparameterized convolutions.
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
-
MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection
MHAF-YOLO reaches 48.9% AP on COCO with 7.1M parameters by combining auxiliary shallow-deep fusion paths and heterogeneous reparameterized convolutions.