ExGate: Externally Controlled Gating for Feature-based Attention in Artificial Neural Networks
This work addresses improving efficiency and accuracy in artificial visual systems, though it appears incremental as it builds on existing attention mechanisms with a specific gating method.
The paper tackled implementing top-down, feature-based attention in artificial neural networks using externally controlled neuron gating, resulting in a 5% increase in classification accuracy on CIFAR-10 and more reasonable prediction errors by reducing misclassifications across different categories.
Perceptual capabilities of artificial systems have come a long way since the advent of deep learning. These methods have proven to be effective, however they are not as efficient as their biological counterparts. Visual attention is a set of mechanisms that are employed in biological visual systems to ease computational load by only processing pertinent parts of the stimuli. This paper addresses the implementation of top-down, feature-based attention in an artificial neural network by use of externally controlled neuron gating. Our results showed a 5% increase in classification accuracy on the CIFAR-10 dataset versus a non-gated version, while adding very few parameters. Our gated model also produces more reasonable errors in predictions by drastically reducing prediction of classes that belong to a different category to the true class.