We present FMAS, a fast multi-objective neural architecture search framework
for semantic segmentation. FMAS subsamples the structure and pre-trained
parameters of DeepLabV3+, without fine-tuning, dramatically reducing training
time during search. To further reduce candidate evaluation time, we use a
subset of the validation dataset during the search. Only the final, Pareto
non-dominated, candidates are ultimately fine-tuned using the complete training
set. We evaluate FMAS by searching for models that effectively trade accuracy
and computational cost on the PASCAL VOC 2012 dataset. FMAS finds competitive
designs quickly, e.g., taking just 0.5 GPU days to discover a DeepLabV3+
variant that reduces FLOPs and parameters by 10$\%$ and 20$\%$ respectively,
for less than 3$\%$ increased error. We also search on an edge device called
GAP8 and use its latency as the metric. FMAS is capable of finding 2.2$\times$
faster network with 7.61$\%$ MIoU loss.

FMAS 是一个快速的多目标神经架构搜索框架，用于语义分割。通过在搜索期间对 DeepLabV3 + 结构和预训练参数进行子采样且无需微调，FMAS 显著减少了训练时间，并使用验证数据集的子集进一步降低候选模型的评估时间。最终，只有最终的 Pareto 非支配候选者才使用完整的训练集进行微调。在 PASCAL VOC 2012 数据集上搜索性能更强且计算成本更低的模型时，FMAS 可以快速找到具有竞争力的设计，例如，在仅使用 0.5 GPU 天的时间内，它可以找到一种 DeepLabV3 + 变体，其 FLOPs 和参数分别减少了 10％和 20％，而误差仅增加了不到 3％。我们还在名为 GAP8 的边缘设备上进行搜索，并使用延迟作为指标。FMAS 可以发现比现有体系结构快 2.2 倍的神经网络，MIoU 损失仅为 7.61％。