Journal ArticleDOI
Spatial Pyramid-Enhanced NetVLAD With Weighted Triplet Loss for Place Recognition
Reads0
Chats0
TLDR
The proposed model defeats the state-of-the-art deep learning approaches applied to place recognition and is easily trained via the standard backpropagation method.Abstract:
We propose an end-to-end place recognition model based on a novel deep neural network. First, we propose to exploit the spatial pyramid structure of the images to enhance the vector of locally aggregated descriptors (VLAD) such that the enhanced VLAD features can reflect the structural information of the images. To encode this feature extraction into the deep learning method, we build a spatial pyramid-enhanced VLAD (SPE-VLAD) layer. Next, we impose weight constraints on the terms of the traditional triplet loss (T-loss) function such that the weighted T-loss (WT-loss) function avoids the suboptimal convergence of the learning process. The loss function can work well under weakly supervised scenarios in that it determines the semantically positive and negative samples of each query through not only the GPS tags but also the Euclidean distance between the image representations. The SPE-VLAD layer and the WT-loss layer are integrated with the VGG-16 network or ResNet-18 network to form a novel end-to-end deep neural network that can be easily trained via the standard backpropagation method. We conduct experiments on three benchmark data sets, and the results demonstrate that the proposed model defeats the state-of-the-art deep learning approaches applied to place recognition.read more
Citations
More filters
Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
TL;DR: A new algorithm for manifold learning and nonlinear dimensionality reduction is presented based on a set of unorganized da-ta points sampled with noise from a parameterized manifold, and the local geometry of the manifold is learned by constructing an approxi-mation for the tangent space at each point.
Proceedings ArticleDOI
Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
TL;DR: Patch-NetVLAD as discussed by the authors combines the advantages of both local and global descriptor methods by deriving patch-level features from NetVLAD residuals, which enables aggregation and matching of deep-learned local features defined over the feature-space grid.
Journal ArticleDOI
An Edge Traffic Flow Detection Scheme Based on Deep Learning in an Intelligent Transportation System
TL;DR: A real-time vehicle tracking counter for vehicles that combines the vehicle detection and vehicle tracking algorithms to realize the detection of traffic flow is proposed.
Journal ArticleDOI
Semantic relation extraction using sequential and tree-structured LSTM with attention
Zhiqiang Geng,Zhiqiang Geng,Guofei Chen,Guofei Chen,Yongming Han,Yongming Han,Gang Lu,Gang Lu,Fang Li,Fang Li +9 more
TL;DR: An end-to-end method that uses bidirectional tree-structured long short-term memory (LSTM) to extract structural features based on the dependency tree of a sentence to enhance the performance of the relation extraction.
Journal ArticleDOI
Image Inpainting: A Review
TL;DR: The work in this paper was made by NPRP grant # NPRP8-140-2-065 from the Qatar National Research Fund (a member of the Qatar Foundation).
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
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.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.