The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
Lightweight Reparameterizable Integral Neural Networks for Mobile Applications
- Published
- Record updated
Summary
Standard integral neural networks are hard to deploy on resource-constrained mobile devices because their training-time and inference-time structures are coupled. The authors propose a continuous reparameterization strategy that converts multiple training-time integration layers into a feed-forward structure at inference, and build lightweight reparameterizable INNs (RINNs) on a MetaFormer-style design. On ImageNet, RINNs reach over 79.1 top-1 accuracy at 0.87 ms latency on mobile devices, and keep their performance at up to 50% structural pruning without fine-tuning.