Image retrieval and classification on deep convolutional SparkNet

@article{Li2016ImageRA,
  title={Image retrieval and classification on deep convolutional SparkNet},
  author={Hongyang Li and Peng Su and Zhizhen Chi and Jingjing Wang},
  journal={2016 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)},
  year={2016},
  pages={1-6}
}
Image retrieval and classification are hot topics in computer vision and have attracted great attention nowadays with the emergence of large-scale data. We propose a new scheme to use both deep learning models and large-scale computing platform and jointly learn powerful feature representations in image classification and retrieval. We achieve a superior performance on the ImageNet dataset, where the framework is easy to be embedded for daily user experience. First we conduct the classification… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-7 OF 7 CITATIONS

Digital Recognition Based on Improved LENET Convolution Neural Network

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Do we really need more training data for object localization

VIEW 1 EXCERPT
CITES BACKGROUND

Enhancing the MapReduce training of BP neural networks based on local weight matrix evolution

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Caffe: Convolutional Architecture for Fast Feature Embedding

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Going deeper with convolutions

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

MapReduce: simplified data processing on large clusters

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Deep semantic ranking based hashing for multi-label image retrieval

VIEW 1 EXCERPT

Revisiting kernelized locality-sensitive hashing for improved large-scale image retrieval

VIEW 1 EXCERPT