ReStNet builds a hybrid model from two pre-trained networks by stitching at the most CKA-similar layer and fine-tuning only the stitching layer, claiming flexible runtime trade-offs for IoT devices.
Pytorch image models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
ReStNet: A Reusable & Stitchable Network for Dynamic Adaptation on IoT Devices
ReStNet builds a hybrid model from two pre-trained networks by stitching at the most CKA-similar layer and fine-tuning only the stitching layer, claiming flexible runtime trade-offs for IoT devices.