Due to data privacy issues, accelerating networks with tiny training sets has become a critical need in practice. Previous methods mainly adopt filter-level pruning to accelerate networks with scarce training samples. In this paper, we reveal that dropping blocks is a fundamentally superior approach in this scenario. It enjoys a higher acceleration ratio and results in a better latency-accuracy performance under the few-shot setting. To choose which blocks to drop, we propose a new concept namely recoverability to measure the difficulty of recovering the compressed network. Our recoverability is efficient and effective for choosing which blocks to drop. Finally, we propose an algorithm named PRACTISE to accelerate networks using only tiny sets of training images. PRACTISE outperforms previous methods by a significant margin. For 22% latency reduction, PRACTISE surpasses previous methods by on average 7% on ImageNet-1k. It also enjoys high generalization ability, working well under data-free or out-of-domain data settings, too. Our code is at https://github.com/DoctorKey/Practise.

翻译：由于数据隐私问题，利用小规模训练集加速网络已成为实际应用中的迫切需求。现有方法主要采用滤波器级剪枝来在训练样本稀缺的场景下加速网络。本文揭示，在这种情况下，丢弃数据块本质上是一种更优的方法。该方法能实现更高的加速比，并在小样本设置下获得更优的延迟-精度性能。为选择需丢弃的数据块，我们提出一种称为"可恢复性"的新概念，用于衡量压缩网络的恢复难度。该指标在筛选待丢弃数据块时兼具高效性与有效性。最终，我们提出名为PRACTISE的算法，仅需少量训练图像即可实现网络加速。PRACTISE的性能显著优于现有方法。在延迟降低22%的条件下，PRACTISE在ImageNet-1k数据集上的平均性能比现有方法提升7%。该方法还具备强泛化能力，在无数据或跨领域数据设置下同样表现优异。我们的代码已开源至https://github.com/DoctorKey/Practise。