CSCO: Connectivity Search of Convolutional Operators

arXiv:2404.17152v1 Announce Type: new
Abstract: Exploring dense connectivity of convolutional operators establishes critical "synapses" to communicate feature vectors from different levels and enriches the set of transformations on Computer Vision applications. Yet, even with heavy-machinery approaches such as Neural Architecture Search (NAS), discovering effective connectivity patterns requires tremendous efforts due to either constrained connectivity design space or a sub-optimal exploration process induced by an unconstrained search space. In this paper, we propose CSCO, a novel paradigm that fabricates effective connectivity …

abstract applications architecture arxiv computer computer vision connectivity convolutional cs.cv feature nas neural architecture search operators patterns search set synapses type vectors vision