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.

本文提出了一种新颖的神经网络模块，可以将现有的单帧语义分割模型转化为视频语义分割流水线，并将过去帧中的语义信息聚合到内存模块中，并通过关注机制来对其进行访问。通过将这些提示与当前帧的编码进行融合，可以改善Cityscapes数据集上的分割性能，并只需增加1.5ms的推理时间。

快速视频语义分割的局部内存注意力