Characterizing and Taming Resolution in Convolutional Neural Networks
This addresses efficiency challenges in large-scale inference systems for computer vision applications, representing an incremental improvement in optimization techniques.
The paper tackles the problem of optimizing image resolution for computer vision models to balance accuracy with computational, storage, and bandwidth costs, proposing a dynamic resolution mechanism that eliminates the need for static choices.
Image resolution has a significant effect on the accuracy and computational, storage, and bandwidth costs of computer vision model inference. These costs are exacerbated when scaling out models to large inference serving systems and make image resolution an attractive target for optimization. However, the choice of resolution inherently introduces additional tightly coupled choices, such as image crop size, image detail, and compute kernel implementation that impact computational, storage, and bandwidth costs. Further complicating this setting, the optimal choices from the perspective of these metrics are highly dependent on the dataset and problem scenario. We characterize this tradeoff space, quantitatively studying the accuracy and efficiency tradeoff via systematic and automated tuning of image resolution, image quality and convolutional neural network operators. With the insights from this study, we propose a dynamic resolution mechanism that removes the need to statically choose a resolution ahead of time.