We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features extracted from several shallower sub-networks. Leveraging the inherent temporal continuity in videos, we distribute these sub-networks over sequential frames. Therefore, at each time step, we only need to perform a lightweight computation to extract a sub-features group from a single sub-network. The full features used for segmentation are then recomposed by application of a novel attention propagation module that compensates for geometry deformation between frames. A grouped knowledge distillation loss is also introduced to further improve the representation power at both full and sub-feature levels. Experiments on Cityscapes, CamVid, and NYUD-v2 demonstrate that our method achieves state-of-the-art accuracy with significantly faster speed and lower latency.
@article{arxiv.2004.01800,
title = {Temporally Distributed Networks for Fast Video Semantic Segmentation},
author = {Ping Hu and Fabian Caba Heilbron and Oliver Wang and Zhe Lin and Stan Sclaroff and Federico Perazzi},
journal= {arXiv preprint arXiv:2004.01800},
year = {2020}
}