用自监督学习在无标签数据上搜出多模态神经网络结构
Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks
- 用自监督学习完成架构搜索与模型预训练
- 仅用无标签数据就成功设计出多模态DNN结构
- 适合缺乏标注数据的多模态任务研究者
神经架构搜索（NAS）可自动化深度神经网络（DNN）的结构设计，受到广泛关注。多模态DNN因需融合多种模态特征，结构复杂，更受益于NAS；然而传统NAS需大量标注数据。本文提出一种针对多模态DNN的自监督学习（SSL）架构搜索方法，将自监督学习应用于架构搜索与模型预训练全过程。实验表明，该方法仅使用无标签训练数据，即可成功设计出多模态深度神经网络架构。
原文摘要 · Abstract (English)
Neural architecture search (NAS), which automates the architectural design process of deep neural networks (DNN), has attracted increasing attention. Multimodal DNNs that necessitate feature fusion from multiple modalities benefit from NAS due to their structural complexity; however, constructing an architecture for multimodal DNNs through NAS requires a substantial amount of labeled training data. Thus, this paper proposes a self-supervised learning (SSL) method for architecture search of multimodal DNNs. The proposed method applies SSL comprehensively for both the architecture search and model pretraining processes. Experimental results demonstrated that the proposed method successfully designed architectures for DNNs from unlabeled training data.
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。