arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01566cs.CVcs.LG
收藏

CG-CNN:通过上下文引导和迁移学习进行自监督特征提取

CG-CNN: Self-Supervised Feature Extraction Through Contextual Guidance and Transfer Learning

Auburn University at Montgomery(奥本大学蒙哥马利分校);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)

Olcay Kursun, Ahmad Patooghy, Peyman Poursani, Oleg V. Favorov

AI总结:

本文提出自监督的 CG-CNN,利用上下文引导和迁移学习从视觉、触觉、时序及文本数据中提取可迁移特征,并在图像与文本任务上验证其优势。

摘要:

上下文引导卷积神经网络(Contextually Guided Convolutional Neural Networks,CG-CNN)利用自监督和上下文信息,在视觉、触觉、时序和文本数据等多种领域中开发可迁移特征。本文通过将 CG-CNN 应用于多种数据集和挑战来展示其适应性,包括 Caltech 和 Brodatz 纹理、VibTac-12 触觉数据集、高光谱图像,以及 XOR 问题和文本分析等挑战。在文本分析中,CG-CNN 采用一种创新的嵌入策略,利用相邻词的上下文进行分类;而在视觉和信号数据中,它通过利用空间信息增强特征提取。CG-CNN 模拟生物神经网络中由上下文引导的无监督学习机制,并且能够在规模有限的数据集上训练以学习其特征。我们在自然图像上的实验结果表明,在可迁移性和分类准确率方面,CG-CNN 优于 AlexNet、ResNet 和 GoogLeNet 等知名深度网络可比较的第一层特征。在文本分析中,CG-CNN 学习到的词嵌入在 20 Newsgroups 文本分类等任务上优于 Word2Vec 等传统模型。此外,正在进行的开发包括在另一个 CG-CNN 的输出上训练 CG-CNN,以探索多层架构,旨在构建更复杂、更具描述性的特征。这种针对多种数据类型的可扩展性和适应性凸显了 CG-CNN 处理广泛应用的潜力,使其成为应对多样化数据表示挑战的一种有前景的架构。

英文摘要:

Contextually Guided Convolutional Neural Networks (CG-CNNs) employ self-supervision and contextual information to develop transferable features across diverse domains, including visual, tactile, temporal, and textual data. This work showcases the adaptability of CG-CNNs through applications to various datasets such as Caltech and Brodatz textures, the VibTac-12 tactile dataset, hyperspectral images, and challenges like the XOR problem and text analysis. In text analysis, CG-CNN employs an innovative embedding strategy that utilizes the context of neighboring words for classification, while in visual and signal data, it enhances feature extraction by exploiting spatial information. CG-CNN mimics the context-guided unsupervised learning mechanisms of biological neural networks and it can be trained to learn its features on limited-size datasets. Our experimental results on natural images reveal that CG-CNN outperforms comparable first-layer features of well-known deep networks such as AlexNet, ResNet, and GoogLeNet in terms of transferability and classification accuracy. In text analysis, CG-CNN learns word embeddings that outperform traditional models like Word2Vec in tasks such as the 20 Newsgroups text classification. Furthermore, ongoing development involves training CG-CNN on outputs from another CG-CNN to explore multi-layered architectures, aiming to construct more complex and descriptive features. This scalability and adaptability to various data types underscore the potential of CG-CNN to handle a wide range of applications, making it a promising architecture for tackling diverse data representation challenges.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑