UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

arXiv:2311.15599v2 Announce Type: replace-cross
Abstract: Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention, but two unresolved and critical issues demand further investigation. 1) The architectures of existing large-kernel ConvNets largely follow the design principles of conventional ConvNets or transformers, while the architectural design for large-kernel ConvNets remains under-addressed. 2) As transformers have dominated multiple modalities, it remains to be investigated whether ConvNets also have a strong universal perception ability in domains beyond vision. In this paper, we …

abstract architectures arxiv attention audio cloud convolutional neural networks cs.ai cs.cv cs.lg demand design image image recognition investigation kernel networks neural networks perception recognition research series transformers type universal video