SdcNet: A Computation-Efficient CNN for Object Recognition
This addresses the problem of computational efficiency for object recognition tasks, offering an incremental improvement with tunable hyperparameters for resource-constrained applications.
The paper tackled the challenge of high computational costs in convolutional neural networks for object recognition by proposing SdcNet, a computation-efficient CNN using SdcBlock modules, which achieved error rates of 5.60% with 55M Flops and 5.24% with 103M Flops on CIFAR-10.
Extracting features from a huge amount of data for object recognition is a challenging task. Convolution neural network can be used to meet the challenge, but it often requires a large number of computation resources. In this paper, a computation-efficient convolutional module, named SdcBlock, is proposed and based on it, the convolution network SdcNet is introduced for object recognition tasks. In the proposed module, optimized successive depthwise convolutions supported by appropriate data management is applied in order to generate vectors containing high density and more varieties of feature information. The hyperparameters can be easily adjusted to suit varieties of tasks under different computation restrictions without significantly jeopardizing the performance. The experiments have shown that SdcNet achieved an error rate of 5.60% in CIFAR-10 with only 55M Flops and also reduced further the error rate to 5.24% using a moderate volume of 103M Flops. The expected computation efficiency of the SdcNet has been confirmed.