The perceptual boost of visual attention is task-dependent in naturalistic settings
This research addresses how attention mechanisms in AI systems adapt to different visual tasks, providing insights for improving computer vision models in real-world applications, though it is incremental in nature.
The study investigated whether the perceptual boost from visual attention varies with task characteristics in naturalistic settings, finding that attention's benefit increases with task difficulty but decreases with larger task sets and higher within-task perceptual similarity.
Top-down attention allows people to focus on task-relevant visual information. Is the resulting perceptual boost task-dependent in naturalistic settings? We aim to answer this with a large-scale computational experiment. First, we design a collection of visual tasks, each consisting of classifying images from a chosen task set (subset of ImageNet categories). The nature of a task is determined by which categories are included in the task set. Second, on each task we train an attention-augmented neural network and then compare its accuracy to that of a baseline network. We show that the perceptual boost of attention is stronger with increasing task-set difficulty, weaker with increasing task-set size and weaker with increasing perceptual similarity within a task set.