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

TL;DR

CG-CNN is a versatile self-supervised neural network architecture that leverages contextual information to learn transferable features across multiple data modalities, outperforming traditional methods in various classification tasks.

Contribution

This work introduces CG-CNN, a novel self-supervised, context-guided CNN framework that adapts across diverse data types and outperforms existing feature extraction methods in transfer learning.

Findings

CG-CNN outperforms AlexNet, ResNet, and GoogLeNet in transferability and accuracy.

In text analysis, CG-CNN embeddings surpass Word2Vec in classification tasks.

Demonstrates adaptability of CG-CNN across visual, tactile, spectral, and textual data.

Abstract

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.