Top-Down Neural Attention by Excitation Backprop

Supplementary Material : Top - down Neural Attention by Excitation Backprop

Excitation Backprop for RNNs

Deep models are state-of-the-art for many vision tasks including video action recognition and video captioning. Models are trained to caption or classify activity in videos, but little is known about the evidence used to make such decisions. Grounding decisions made by deep networks has been studied in spatial visual content, giving more insight into model predictions for images. However, such ...

Top-down modulation of attention by emotion

Due to their evolutionary salience, threatrelated stimuli, such as snakes, spiders, and angry faces constitute a special class of stimuli believed to capture attention in an involuntary, bottom-up manner. Most research in affective neuroscience has focused on unraveling neural pathways that support this “automatic” capture of attention by emotional stimuli (Vuilleumier and Driver, 2007). Howeve...

Mechanisms of top-down attention.

Attention exhibits characteristic neural signatures in brain regions that process sensory signals. An important area of future research is to understand the nature of top-down signals that facilitate attentional guidance towards behaviorally relevant locations and features. In this review, we discuss recent studies that have made progress towards understanding: (i) the brain structures and circ...

Top-down attention selection is fine grained.

Although much is known about the sources and modulatory effects of top-down attentional signals, the information capacity of these signals is less known. Here, we investigate the granularity of top-down attentional signals. Previous theories in psychophysics have provided conflicting evidence on whether top-down guidance is coarse grained (i.e., one gain control term per feature dimension) or f...