no code implementations • 6 Apr 2022 • Tugberk Erol, Duygu Sarikaya
With PlutoNet, we propose a novel \emph{decoder consistency training} approach that consists of a shared encoder, the modified partial decoder which is a combination of the partial decoder and full-scale connections that capture salient features at different scales without being redundant, and the auxiliary decoder which focuses on higher-level relevant semantic features.
no code implementations • 8 Mar 2022 • Tugberk Erol, Duygu Sarikaya
Our proposed model requires fewer parameters as well as outperforms the state-of-the-art models.