Res2Net: A New Multi-scale Backbone Architecture

Shang-Hua GaoMing-Ming ChengKai ZhaoXin-Yu ZhangMing-Hsuan YangPhilip Torr

   Papers with code   Abstract  PDF

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications... (read more)

Benchmarked Models