Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

Abstract

It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent on the changing real-time resource availability. Thus, it is inadequate to train just inference-efficient CNNs, whose inference costs are not adjustable and cannot adapt to varied inference budgets. We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint). During training, SDPoint applies feature map downsampling to a random point in the layer hierarchy, with a random downsampling ratio. The different stochastic downsampling configurations known as SDPoint instances (of the same model) have computational costs different from each other, while being trained to minimize the same prediction loss. Sharing network parameters across different instances provides significant regularization boost. During inference, one may handpick a SDPoint instance that best fits the inference budget. The effectiveness of SDPoint, as both a cost-adjustable inference approach and a regularizer, is validated through extensive experiments on image classification.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Going Deeper with Convolutions
• Trained Ternary Quantization
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• YOLO9000: Better, Faster, Stronger
• Channel Pruning for Accelerating Very Deep Neural Networks
• Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
• Memory-Efficient Implementation of DenseNets
• BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks