CMSA, a grouped multi-head attention with cascaded multi-scale feature fusion, improves accuracy on low-resolution pose estimation and CIFAR classification while using far fewer parameters than prior models.
Lite pose: Efficient architecture design for 2d human pose estimation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images
CMSA, a grouped multi-head attention with cascaded multi-scale feature fusion, improves accuracy on low-resolution pose estimation and CIFAR classification while using far fewer parameters than prior models.