Parameter-Free Channel Attention for Image Classification and Super-Resolution
This work addresses the problem of computational efficiency in deep learning for image processing, offering a parameter-free solution that is incremental but beneficial for researchers and practitioners in computer vision.
The authors tackled the issue of increased parameters and computational costs in channel attention mechanisms by proposing a Parameter-Free Channel Attention (PFCA) module, which improved performance on image classification and super-resolution tasks without significant parameter or FLOPs growth, as validated on datasets like CIFAR-100, ImageNet, and DIV2K.
The channel attention mechanism is a useful technique widely employed in deep convolutional neural networks to boost the performance for image processing tasks, eg, image classification and image super-resolution. It is usually designed as a parameterized sub-network and embedded into the convolutional layers of the network to learn more powerful feature representations. However, current channel attention induces more parameters and therefore leads to higher computational costs. To deal with this issue, in this work, we propose a Parameter-Free Channel Attention (PFCA) module to boost the performance of popular image classification and image super-resolution networks, but completely sweep out the parameter growth of channel attention. Experiments on CIFAR-100, ImageNet, and DIV2K validate that our PFCA module improves the performance of ResNet on image classification and improves the performance of MSRResNet on image super-resolution tasks, respectively, while bringing little growth of parameters and FLOPs.