Open AccessPosted Content
Exploiting Local Features from Deep Networks for Image Retrieval
TLDR
In this article, the authors show that for instance-level image retrieval, lower layers often perform better than the last layers in convolutional neural networks, and adopt VLAD encoding to encode features into a single vector for each image.Abstract:
Deep convolutional neural networks have been successfully applied to image classification tasks. When these same networks have been applied to image retrieval, the assumption has been made that the last layers would give the best performance, as they do in classification. We show that for instance-level image retrieval, lower layers often perform better than the last layers in convolutional neural networks. We present an approach for extracting convolutional features from different layers of the networks, and adopt VLAD encoding to encode features into a single vector for each image. We investigate the effect of different layers and scales of input images on the performance of convolutional features using the recent deep networks OxfordNet and GoogLeNet. Experiments demonstrate that intermediate layers or higher layers with finer scales produce better results for image retrieval, compared to the last layer. When using compressed 128-D VLAD descriptors, our method obtains state-of-the-art results and outperforms other VLAD and CNN based approaches on two out of three test datasets. Our work provides guidance for transferring deep networks trained on image classification to image retrieval tasks.read more
Citations
More filters
Book ChapterDOI
Deep Image Retrieval: Learning Global Representations for Image Search
TL;DR: This work proposes a novel approach for instance-level image retrieval that produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors by leveraging a ranking framework and projection weights to build the region features.
Proceedings ArticleDOI
Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers
TL;DR: In this paper, two new strategies to detect objects accurately and efficiently using deep convolutional neural network are investigated: scale-dependent pooling and layerwise cascaded rejection classifiers.
Journal ArticleDOI
End-to-End Learning of Deep Visual Representations for Image Retrieval
TL;DR: In this article, the authors leverage a large-scale but noisy landmark dataset and develop an automatic cleaning method that produces a suitable training set for deep retrieval, and train this network with a siamese architecture that combines three streams with a triplet loss.
Posted Content
SIFT Meets CNN: A Decade Survey of Instance Retrieval
Liang Zheng,Yi Yang,Qi Tian +2 more
TL;DR: A comprehensive survey of instance retrieval over the last decade is presented in this paper, where two broad categories, SIFT-based and CNN-based methods, are presented, according to the codebook size, and the literature is organized into using large/medium-sized/small codebooks.
Posted Content
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
Wieland Brendel,Matthias Bethge +1 more
TL;DR: A high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain is introduced, and behaves similar to state-of-the art deep neural networks such as VGG-16, ResNet-152 or DenseNet-169 in terms of feature sensitivity, error distribution and interactions between image parts.
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).
Book ChapterDOI
Visualizing and Understanding Convolutional Networks
Matthew D. Zeiler,Rob Fergus +1 more
TL;DR: A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.