High-Level Features Parallelization for Inference Cost Reduction Through Selective Attention. (arXiv:2308.05128v1 [cs.CV])

In this work, we parallelize high-level features in deep networks to
selectively skip or select class-specific features to reduce inference costs.
This challenges most deep learning methods due to their limited ability to
efficiently and effectively focus on selected class-specific features without
retraining. We propose a serial-parallel hybrid architecture with serial
generic low-level features and parallel high-level features. This accounts for
the fact that many high-level features are class-specific rather than generic,
and has connections to recent neuroscientific findings that …

arxiv attention challenges cost costs deep learning features focus hybrid inference networks parallelization reduce through work