Abstract
We propose a novel neural network module that transforms an existing single-frame semantic segmentation model into a video semantic segmentation pipeline. In contrast to prior works, we strive towards a simple and general module that can be integrated into virtually any single-frame architecture. Our approach aggregates a rich representation of the semantic information in past frames into a memory module. Information stored in the memory is then accessed through an attention mechanism. This provides temporal appearance cues from prior frames, which are then fused with an encoding of the current frame through a second attention-based module. The segmentation decoder processes the fused representation to predict the final semantic segmentation. We integrate our approach into two popular semantic segmentation networks: ERFNet and PSPNet. We observe an improvement in segmentation performance on Cityscapes by 1.7% and 2.1% in mIoU respectively, while increasing inference time of ERFNet by only 1.5ms.
Abstract (translated)
URL
https://arxiv.org/abs/2101.01715
