Learning Non-Metric Visual Similarity for Image Retrieval

@article{Garcia2019LearningNV,
  title={Learning Non-Metric Visual Similarity for Image Retrieval},
  author={Noa Garcia and G. Vogiatzis},
  journal={Image Vis. Comput.},
  year={2019},
  volume={82},
  pages={18-25}
}
  • Noa Garcia, G. Vogiatzis
  • Published 2019
  • Computer Science, Mathematics
  • Image Vis. Comput.
  • Measuring visual (dis)similarity between two or more instances within a data distribution is a fundamental task in many applications, specially in image retrieval. Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the similarity model. In this work, we analyze a simple approach for deep learning networks to be used as an approximation of non-metric… CONTINUE READING
    Optical-to-SAR image registration using a combination of CNN descriptors and cross-correlation coefficient
    Deformation-Aware 3D Model Embedding and Retrieval
    3
    An efficient bi-layer content based image retrieval system
    2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 68 REFERENCES
    Learning Fine-Grained Image Similarity with Deep Ranking
    766
    Large Scale Online Learning of Image Similarity Through Ranking
    294
    Visual Instance Retrieval with Deep Convolutional Networks
    210
    Deep Metric Learning Using Triplet Network
    699
    Deep Image Retrieval: Learning Global Representations for Image Search
    433
    Learning to compare image patches via convolutional neural networks
    821
    Online multimodal deep similarity learning with application to image retrieval
    129
    Deep Learning for Content-Based Image Retrieval: A Comprehensive Study
    566
    Learning Non-Metric Partial Similarity Based on Maximal Margin Criterion
    28