Journal ArticleDOI
Scene Classification Using Hierarchical Wasserstein CNN
TLDR
This paper finds that for two distributions in hierarchically organized data space, WD has a closed-form solution, which is called “hierarchical WD (HWD),” and uses this theory to construct novel loss functions that overcome the shortcomings of CE loss.Abstract:
In multiclass classification, convolutional neural network (CNN) is generally coupled with the cross-entropy (CE) loss, which only penalizes the predicted probability corresponding to a ground truth class and ignores the interclass relationship. We argue that CNN can be improved by using a better loss function. On the other hand, the Wasserstein distance (WD) is a well-known metric used to measure the distance between two distributions. Directly solving the WD problem requires a prohibitively large amount of computation time, whereas the cheaper iterative algorithms have a variety of shortcomings such as computational instability and difficulty in selecting parameters. In this paper, we address these issues by giving an analytical solution to the WD problem—for the first time, we find that for two distributions in hierarchically organized data space, WD has a closed-form solution, which we call “hierarchical WD (HWD).” We use this theory to construct novel loss functions that overcome the shortcomings of CE loss. To this end, multi-CNN information fusion that provides the basis for building category hierarchies is carried out first. Then, the semantic relationship among classes is modeled as a binary tree. Then, CNN coupled with an HWD-based loss, i.e., hierarchical Wasserstein CNN (HW-CNN), is trained to learn deep features. In this way, prior knowledge about the interclass relationship is embedded into HW-CNN, and information from several CNNs provides guidance in the process of training individual HW-CNNs. We conducted extensive experiments over two publicly available remote sensing data sets and achieved a state-of-the-art performance in scene classification tasks.read more
Citations
More filters
Journal ArticleDOI
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
TL;DR: This article provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers and discusses the main challenges of remote sensing images classification and survey.
Journal ArticleDOI
Review of Image Classification Algorithms Based on Convolutional Neural Networks
TL;DR: In this paper, a review of the application of CNNs to image classification tasks is presented, which focuses on their development, from their predecessors up to recent state-of-the-art (SOAT) network architectures.
Journal ArticleDOI
Similarity-Based Unsupervised Deep Transfer Learning for Remote Sensing Image Retrieval
TL;DR: This work applies unsupervised transfer learning to CNN training to transform similarity learning into deep ordinal classification with the help of several CNN experts pretrained over large-scale-labeled everyday image sets, which jointly determine image similarities and provide pseudolabels for classification.
Journal ArticleDOI
High-Resolution Remote Sensing Image Scene Classification via Key Filter Bank Based on Convolutional Neural Network
TL;DR: A key region or location capturing method called key filter bank (KFB) is proposed in this article, and KFB can retain global information at the same time and can combine with different CNN models to improve the performance of HRRS imagery scene classification.
Journal ArticleDOI
Combing Triple-Part Features of Convolutional Neural Networks for Scene Classification in Remote Sensing
Hong Huang,Kejie Xu +1 more
TL;DR: Experiments demonstrate that the proposed CTFCNN method performs significantly better than some state-of-the-art methods, and the overall accuracy can reach 98.44% and 94.91%, respectively, indicates thatThe proposed framework can provide a discriminating description for HSRRS images.
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.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Journal ArticleDOI
Normalized cuts and image segmentation
Jianbo Shi,Jitendra Malik +1 more
TL;DR: This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.