Parameter-Free Average Attention Improves Convolutional Neural Network Performance (Almost) Free of Charge
This provides an easy-to-use module for computer vision tasks, but it is incremental as it builds on existing attention mechanisms without introducing a new paradigm.
The paper tackles the problem of improving convolutional neural network performance by introducing PfAAM, a parameter-free attention mechanism that highlights salient image regions, resulting in improved performance for classification and semantic segmentation across multiple architectures with minimal computational overhead.
Visual perception is driven by the focus on relevant aspects in the surrounding world. To transfer this observation to the digital information processing of computers, attention mechanisms have been introduced to highlight salient image regions. Here, we introduce a parameter-free attention mechanism called PfAAM, that is a simple yet effective module. It can be plugged into various convolutional neural network architectures with a little computational overhead and without affecting model size. PfAAM was tested on multiple architectures for classification and segmentic segmentation leading to improved model performance for all tested cases. This demonstrates its wide applicability as a general easy-to-use module for computer vision tasks. The implementation of PfAAM can be found on https://github.com/nkoerb/pfaam.