论文标题
classPruning：通过动态N：M修剪加快图像恢复网络
ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning
论文作者
论文摘要
随着深度神经网络的快速发展，图像恢复任务已实现了巨大的性能提高。但是，大多数普遍的深度学习模型在静态上进行推断，忽略不同的图像具有不同的恢复困难，并且略微退化的图像可以通过纤细的子网恢复。为此，我们提出了一种新的解决方案管道，称为“类”，该管道利用具有不同功能的网络来处理具有不同恢复困难的图像。特别是，我们使用轻质分类器来识别图像恢复难度，然后可以根据预测的难度通过在基础恢复网络上执行动态N：细粒度的结构化修剪来根据预测的难度进行采样。我们进一步提出了一种新颖的培训策略以及两个额外的损失条款，以稳定训练并提高绩效。实验表明，集体修复可以帮助现有方法在保持性能的同时节省大约40％的失败。
Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have varying restoration difficulties and lightly degraded images can be well restored by slimmer subnetworks. To this end, we propose a new solution pipeline dubbed ClassPruning that utilizes networks with different capabilities to process images with varying restoration difficulties. In particular, we use a lightweight classifier to identify the image restoration difficulty, and then the sparse subnetworks with different capabilities can be sampled based on predicted difficulty by performing dynamic N:M fine-grained structured pruning on base restoration networks. We further propose a novel training strategy along with two additional loss terms to stabilize training and improve performance. Experiments demonstrate that ClassPruning can help existing methods save approximately 40% FLOPs while maintaining performance.
