统一卷积、Transformer等架构搜索空间，发现更优新模型
Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between
- 基于图结构统一构建神经网络搜索空间
- 在相同训练条件下超越主流人工设计模型
- 提供标准化工具促进公平比较与复现
我们提出通用神经网络架构空间（UniNAS），一个可统一卷积网络、Transformer及其混合架构的通用神经架构搜索（NAS）框架。该方法支持发现新型架构，并在统一框架下分析已有架构。我们还设计了一种新搜索算法，可有效遍历该空间，并验证其包含性能优异的新架构——在相同训练设置下，优于当前最先进的手工设计模型。此外，我们发布了一个统一工具包，包含标准化的训练与评估协议，以提升研究可复现性并实现公平比较。本工作为从图视角系统探索全谱神经架构开辟了新路径。
原文摘要 · Abstract (English)
We introduce Universal Neural Architecture Space (UniNAS), a generic search space for neural architecture search (NAS) which unifies convolutional networks, transformers, and their hybrid architectures under a single, flexible framework. Our approach enables discovery of novel architectures as well as analyzing existing architectures in a common framework. We also propose a new search algorithm that allows traversing the proposed search space, and demonstrate that the space contains interesting architectures, which, when using identical training setup, outperform state-of-the-art hand-crafted architectures. Finally, a unified toolkit including a standardized training and evaluation protocol is introduced to foster reproducibility and enable fair comparison in NAS research. Overall, this work opens a pathway towards systematically exploring the full spectrum of neural architectures with a unified graph-based NAS perspective.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。