论文标题
任何宽度网络
Any-Width Networks
论文作者
论文摘要
尽管速度和准确性取得了显着提高，但在推理时期，卷积神经网络（CNN）通常仍作为整体实体运行。这对资源受限的实用应用构成了挑战，在这种应用程序中，计算预算和绩效需求都可能随着情况而变化。为了解决这些限制，我们提出了任何宽度网络（AWN），可调宽度的CNN体系结构和相关的训练例程，允许对推理期间的速度和准确性进行细粒度的控制。我们的关键创新是使用低三角形的重量矩阵，这些矩阵明确地解决了宽度各不相同的批处理统计数据，同时自然适合多宽度操作。我们还表明，这种设计有助于基于随机宽度采样的有效训练程序。我们从经验上证明，我们提出的awn与现有方法相比，在推断过程中提供最大颗粒状的控制。
Despite remarkable improvements in speed and accuracy, convolutional neural networks (CNNs) still typically operate as monolithic entities at inference time. This poses a challenge for resource-constrained practical applications, where both computational budgets and performance needs can vary with the situation. To address these constraints, we propose the Any-Width Network (AWN), an adjustable-width CNN architecture and associated training routine that allow for fine-grained control over speed and accuracy during inference. Our key innovation is the use of lower-triangular weight matrices which explicitly address width-varying batch statistics while being naturally suited for multi-width operations. We also show that this design facilitates an efficient training routine based on random width sampling. We empirically demonstrate that our proposed AWNs compare favorably to existing methods while providing maximally granular control during inference.
