Corpus ID: 54557498

Learning Large Euclidean Margin for Sketch-based Image Retrieval

@article{Lu2018LearningLE,
  title={Learning Large Euclidean Margin for Sketch-based Image Retrieval},
  author={Peng Lu and Gao Huang and Yanwei Fu and Guodong Guo and Hangyu Lin},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.04275}
}
  • Peng Lu, Gao Huang, +2 authors Hangyu Lin
  • Published 2018
  • Computer Science
  • ArXiv
  • This paper addresses the problem of Sketch-Based Image Retrieval (SBIR), for which bridge the gap between the data representations of sketch images and photo images is considered as the key. Previous works mostly focus on learning a feature space to minimize intra-class distances for both sketches and photos. In contrast, we propose a novel loss function, named Euclidean Margin Softmax (EMS), that not only minimizes intra-class distances but also maximizes inter-class distances simultaneously… CONTINUE READING
    Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
    11
    Bi-Directional Domain Translation for Zero-Shot Sketch-Based Image Retrieval
    1
    Conditional Image Retrieval
    Representative Feature Matching Network for Image Retrieval
    Deep Learning for Free-Hand Sketch: A Survey
    • P. Xu
    • Computer Science
    • 2020
    8

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES
    A Zero-Shot Framework for Sketch-based Image Retrieval
    42
    Zero-Shot Sketch-Image Hashing
    43
    Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval
    115
    SketchNet: Sketch Classification with Web Images
    50
    Sketch based Image Retrieval using Learned KeyShapes (LKS)
    52
    Sketch-based image retrieval via Siamese convolutional neural network
    103
    Sketch Me That Shoe
    179
    Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval
    74
    Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
    24
    Sketch-based 3D shape retrieval using Convolutional Neural Networks
    228