CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities
📰 ArXiv cs.AI
arXiv:2603.26425v1 Announce Type: cross Abstract: Recent research on vision backbone architectures has predominantly focused on optimizing efficiency for hardware platforms with high parallel processing capabilities. This category increasingly includes embedded systems such as mobile phones and embedded AI accelerator modules. In contrast, CPUs do not have the possibility to parallelize operations in the same manner, wherefore models benefit from a specific design philosophy that balances amount
DeepCamp AI