@InProceedings{DannaXue2022,
author="Danna Xue
and Fei Yang
and Pei Wang
and Luis Herranz
and Jinqiu Sun
and Yu Zhu
and Yanning Zhang",
title="SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision",
booktitle="30th ACM International Conference on Multimedia",
year="2022",
publisher="Association for Computing Machinery",
pages="6539--6548",
abstract="Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these models cannot flexibly adapt to varying accuracy and efficiency requirements. In this paper, we propose a simple but effective slimmable semantic segmentation (SlimSeg) method, which can be executed at different capacities during inference depending on the desired accuracy-efficiency tradeoff. More specifically, we employ parametrized channel slimming by stepwise downward knowledge distillation during training. Motivated by the observation that the differences between segmentation results of each submodel are mainly near the semantic borders, we introduce an additional boundary guided semantic segmentation loss to further improve the performance of each submodel. We show that our proposed SlimSeg with various mainstream networks can produce flexible models that provide dynamic adjustment of computational cost and better performance than independent models. Extensive experiments on semantic segmentation benchmarks, Cityscapes and CamVid, demonstrate the generalization ability of our framework.",
optnote="MACO; 600.161; 601.400",
optnote="exported from refbase (http://158.109.8.37/show.php?record=3758), last updated on Mon, 24 Apr 2023 13:03:15 +0200",
isbn="978-1-4503-9203-7",
doi="10.1145/3503161.3548191",
file=":http://158.109.8.37/files/XYW2022.pdf:PDF"
}