Proceedings ArticleDOI
Deep transfer learning with ontology for image classification
Umang Gupta,Santanu Chaudhury +1 more
- pp 1-4
TLDR
This algorithm combines CNN and ontology priors to infer abstract patterns in Indian Monument Images using a transfer learning based approach and demonstrates that the method improves remarkably over logistic classifier and other transfer learning approach.Abstract:
Purely, data-driven large scale image classification has been achieved using various feature descriptors like SIFT, HOG etc. Major milestone in this regards is Convolutional Neural Networks (CNN) based methods which learn optimal feature descriptors as filters. Little attention has been given to the use of domain knowledge. Ontology plays an important role in learning to categorize images into abstract classes where there may not be a clear visual connect between category and image, for example identifying image mood — happy, sad and neutral. Our algorithm combines CNN and ontology priors to infer abstract patterns in Indian Monument Images. We use a transfer learning based approach in which, knowledge of domain is transferred to CNN while training (top down transfer) and inference is made using CNN prediction and ontology tree/priors (bottom up transfer ). We classify images to categories like Tomb, Fort and Mosque. We demonstrate that our method improves remarkably over logistic classifier and other transfer learning approach. We conclude with a remark on possible applications of the model and note about scaling this to bigger ontology.read more
Citations
More filters
Journal ArticleDOI
Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection
TL;DR: An elaborately designed deep hierarchical network, namely a contextual region-based convolutional neural network with multilayer fusion, for SAR ship detection, which is composed of a region proposal network (RPN) with high network resolution and an object detection network with contextual features.
Book ChapterDOI
Using Relational Concept Networks for Explainable Decision Support
TL;DR: A controlled automated support tool for gaining situational understanding, where multiple sources of information are integrated and sub-symbolic information and technologies with symbolic knowledge and technologies from experts or ontologies are combined.
Patent
Generating and using a knowledge base for image classification
TL;DR: In this article, a knowledge base (KB) is generated and used to classify images and representative images are obtained from one or more image sources based on the subcategories identified by the KB.
Journal ArticleDOI
A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information
TL;DR: This paper proposed a novel classification framework using the multispace image reconstruction inputs and the transfer learning technology, and demonstrated the performance advantages by comparing with the related works.
Proceedings ArticleDOI
Review of the Application of Ontology in the Field of Image Object Recognition
TL;DR: It is found that combining ontology knowledge model and traditional image recognition technology can improve recognition accuracy, enhance high-level semantic recognition ability, reduce the demand of the large number of training samples, and improve the scalability of the image recognition system.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Book ChapterDOI
Learning internal representations by error propagation
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
Book
Learning internal representations by error propagation
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
Posted Content
Rich feature hierarchies for accurate object detection and semantic segmentation
TL;DR: This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Related Papers (5)
Enhanced visual attention-guided deep neural networks for image classification
Deep learning vs. bag of features in machine learning for image classification
Sehla Loussaief,Afef Abdelkrim +1 more