论文标题
用于图像分类的微调飞镖
Fine-Tuning DARTS for Image Classification
论文作者
论文摘要
由于卓越的分类性能，神经体系结构搜索（NAS）吸引了吸引力。微分体系结构搜索（飞镖）是一种计算轻度方法。限制计算资源，飞镖是许多近似值。这些近似值导致表现较低。我们建议使用固定操作对飞镖进行微调，因为它们与这些近似值无关。我们的方法在参数数量和分类精度之间提供了良好的权衡。与最先进的方法相比，我们的方法将Fashion-Mio-TCAR和MIO-TCD数据集的前1位准确性提高了0.56％，0.50％和0.39％。我们的方法的表现要比飞镖更好，与DARTS相比，在CIFAR-10，CIFAR-100，时尚企业，Compcars，Compcars和Mio-TCD数据集上，将精度提高了0.28％，1.64％，0.34％，4.5％和3.27％。
Neural Architecture Search (NAS) has gained attraction due to superior classification performance. Differential Architecture Search (DARTS) is a computationally light method. To limit computational resources DARTS makes numerous approximations. These approximations result in inferior performance. We propose to fine-tune DARTS using fixed operations as they are independent of these approximations. Our method offers a good trade-off between the number of parameters and classification accuracy. Our approach improves the top-1 accuracy on Fashion-MNIST, CompCars, and MIO-TCD datasets by 0.56%, 0.50%, and 0.39%, respectively compared to the state-of-the-art approaches. Our approach performs better than DARTS, improving the accuracy by 0.28%, 1.64%, 0.34%, 4.5%, and 3.27% compared to DARTS, on CIFAR-10, CIFAR-100, Fashion-MNIST, CompCars, and MIO-TCD datasets, respectively.
