High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attention

arXiv:2308.05128v2 Announce Type: replace
Abstract: This paper introduces a novel network topology that seamlessly integrates dynamic inference cost with a top-down attention mechanism, addressing two significant gaps in traditional deep learning models. Drawing inspiration from human perception, we combine sequential processing of generic low-level features with parallelism and nesting of high-level features. This design not only reflects a finding from recent neuroscience research regarding - spatially and contextually distinct neural activations - in human cortex, but also introduces a novel …

abstract arxiv attention cost cs.cv deep learning dynamic features human inference inspiration low network novel paper perception processing topology type