PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

13 Jul 2020Duo LiAnbang YaoQifeng Chen

Despite their strong modeling capacities, Convolutional Neural Networks (CNNs) are often scale-sensitive. For enhancing the robustness of CNNs to scale variance, multi-scale feature fusion from different layers or filters attracts great attention among existing solutions, while the more granular kernel space is overlooked... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper