Multi-Scale Feature Representations¶
PANet¶
adds an extra bottom-up path aggregation network on top of FPN
STDL¶
proposes a scale-transfer module to exploit cross-scale features
M2det¶
proposes a U-shape module to fuse multi-scale features
G-FRNet¶
introduces gate units for controlling information flow across features
NAS-FPN¶
autoML/NAS-FPN leverages neural architecture search to automatically design feature network topology.