Enhancing sensor resolution improves CNN accuracy given the same number of parameters or FLOPS
This addresses efficiency challenges in computer vision for resource-constrained applications, but it is incremental as it builds on prior work like EfficientNet.
The paper tackles the trade-off between input resolution and computational cost in CNNs, showing that modifying networks to use higher resolution can improve accuracy while keeping parameters or FLOPS constant, with preliminary results on datasets like MNIST and CIFAR10.
High image resolution is critical to obtain a good performance in many computer vision applications. Computational complexity of CNNs, however, grows significantly with the increase in input image size. Here, we show that it is almost always possible to modify a network such that it achieves higher accuracy at a higher input resolution while having the same number of parameters or/and FLOPS. The idea is similar to the EfficientNet paper but instead of optimizing network width, depth and resolution simultaneously, here we focus only on input resolution. This makes the search space much smaller which is more suitable for low computational budget regimes. More importantly, by controlling for the number of model parameters (and hence model capacity), we show that the additional benefit in accuracy is indeed due to the higher input resolution. Preliminary empirical investigation over MNIST, Fashion MNIST, and CIFAR10 datasets demonstrates the efficiency of the proposed approach.