CSCO: Connectivity Search of Convolutional Operators
CoRR(2024)
摘要
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
hand-crafted and NAS-crafted dense connectivity. Our code is publicly
available.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要