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 of convolutional operators with minimal utilization of existing design motifs and further utilizes the discovered wiring to construct high-performing ConvNets. CSCO guides the exploration via a neural predictor as a surrogate of the ground-truth performance. We introduce Graph Isomorphism as data augmentation to improve sample efficiency and propose a Metropolis-Hastings Evolutionary Search (MH-ES) to evade locally optimal architectures and advance search quality. Results on ImageNet show ~0.6% performance improvement over hand-crafted and NAS-crafted dense connectivity. Our code is publicly available.
View on arXiv@article{zhang2025_2404.17152,
title={ CSCO: Connectivity Search of Convolutional Operators },
author={ Tunhou Zhang and Shiyu Li and Hsin-Pai Cheng and Feng Yan and Hai Li and Yiran Chen },
journal={arXiv preprint arXiv:2404.17152},
year={ 2025 }
}