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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kursun, Olcay, Patooghy, Ahmad, Poursani, Peyman, Favorov, Oleg V.
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929555849084928
author Kursun, Olcay
Patooghy, Ahmad
Poursani, Peyman
Favorov, Oleg V.
author_facet Kursun, Olcay
Patooghy, Ahmad
Poursani, Peyman
Favorov, Oleg V.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2103_01566
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle CG-CNN: Self-Supervised Feature Extraction Through Contextual Guidance and Transfer Learning
Kursun, Olcay
Patooghy, Ahmad
Poursani, Peyman
Favorov, Oleg V.
Computer Vision and Pattern Recognition
Machine Learning
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.
title CG-CNN: Self-Supervised Feature Extraction Through Contextual Guidance and Transfer Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2103.01566