• Corpus ID: 239998112

CBIR using Pre-Trained Neural Networks

  title={CBIR using Pre-Trained Neural Networks},
  author={Agnel Lazar Alappat and Prajwal Nakhate and Sagar Suman and Ambarish Chandurkar and Varad Pimpalkhute and Tapan Jain},
Much of the recent research work in image retrieval, has been focused around using Neural Networks as the core component. Many of the papers in other domain have shown that training multiple models, and then combining their outcomes, provide good results. This is since, a single Neural Network model, may not extract sufficient information from the input. In this paper, we aim to follow a different approach. Instead of the using a single model, we use a pretrained Inception V3 model, and extract… 

Figures and Tables from this paper


Exploiting local features from deep networks for image retrieval
  • J. Ng, F. Yang, L. Davis
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2015
This work provides guidance for transferring deep networks trained on image classification to image retrieval tasks, and presents an approach for extracting convolutional features from different layers of the networks, and adopts VLAD encoding to encode features into a single vector for each image.
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
SIFT Meets CNN: A Decade Survey of Instance Retrieval
A comprehensive survey of instance retrieval over the last decade, presenting milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods.
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
A series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13 suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.
Combination of Multiple Global Descriptors for Image Retrieval
A novel framework that exploits multiple global descriptors to get an ensemble effect while it can be trained in an end-to-end manner is proposed, which achieves the state-of-the-art performance on the CARS196, CUB200-2011, In-shop Clothes, and Stanford Online Products on image retrieval tasks.
Very Deep Convolutional Networks for Large-Scale Image Recognition
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.
Bilinear CNN Models for Fine-Grained Visual Recognition
We propose bilinear models, a recognition architecture that consists of two feature extractors whose outputs are multiplied using outer product at each location of the image and pooled to obtain an
Particular object retrieval with integral max-pooling of CNN activations
This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN, and significantly improves existing CNN-based recognition pipeline.
Improving the Fisher Kernel for Large-Scale Image Classification
In an evaluation involving hundreds of thousands of training images, it is shown that classifiers learned on Flickr groups perform surprisingly well and that they can complement classifier learned on more carefully annotated datasets.
Deep dictionary learning for fine-grained image classification
An on-line dictionary learning algorithm where the principle of sparsity is integrated into classification is proposed, where training data can be represented with a less number of dictionary atoms, and makes classification much more efficient.