PlutoNet: An efficient polyp segmentation network with modified partial decoder and decoder consistency training

Deep learning models are used to minimize the number of polyps that goes unnoticed by the experts and to accurately segment the detected polyps during interventions. Although state-of-the-art models are proposed, it remains a challenge to define representations that are able to generalize well and that mediate between capturing low-level features and higher-level semantic details without being redundant. Another challenge with these models is that they are computation and memory intensive, which can pose a problem with real-time applications. To address these problems, PlutoNet is proposed for polyp segmentation which requires only 9 FLOPs and 2,626,537 parameters, less than 10% of the parameters required by its counterparts. With PlutoNet, a novel <i>decoder consistency training</i> approach is proposed that consists of a shared encoder, the <i>modified partial decoder</i>, which is a combination of the partial decoder and full-scale connections that capture salient features at different scales without redundancy, and the auxiliary decoder which focuses on higher-level semantic features. The <i>modified partial decoder</i> and the auxiliary decoder are trained with a combined loss to enforce consistency, which helps strengthen learned representations. Ablation studies and experiments are performed which show that PlutoNet performs significantly better than the state-of-the-art models, particularly on unseen datasets.