Width Transfer: On the (In)variance of Width Optimization
This addresses the efficiency issue in CNN training for researchers and practitioners, though it is incremental as it builds on existing width optimization methods.
The paper tackled the problem of high computational overhead in optimizing channel counts for CNNs by proposing width transfer, which leverages the regularity of optimized widths across sizes and depths, achieving up to a 320x reduction in overhead without compromising top-1 accuracy on ImageNet.
Optimizing the channel counts for different layers of a CNN has shown great promise in improving the efficiency of CNNs at test-time. However, these methods often introduce large computational overhead (e.g., an additional 2x FLOPs of standard training). Minimizing this overhead could therefore significantly speed up training. In this work, we propose width transfer, a technique that harnesses the assumptions that the optimized widths (or channel counts) are regular across sizes and depths. We show that width transfer works well across various width optimization algorithms and networks. Specifically, we can achieve up to 320x reduction in width optimization overhead without compromising the top-1 accuracy on ImageNet, making the additional cost of width optimization negligible relative to initial training. Our findings not only suggest an efficient way to conduct width optimization but also highlight that the widths that lead to better accuracy are invariant to various aspects of network architectures and training data.