Unsupervised Representation Learning by Discovering Reliable Image Relations

  title={Unsupervised Representation Learning by Discovering Reliable Image Relations},
  author={Timo Milbich and Omair Ghori and F. Diego and Bjorn Ommer},
  journal={Pattern Recognit.},
  • Timo Milbich, Omair Ghori, +1 author Bjorn Ommer
  • Published 2020
  • Computer Science
  • Pattern Recognit.
  • Learning robust representations that allow to reliably establish relations between images is of paramount importance for virtually all of computer vision. Annotating the quadratic number of pairwise relations between training images is simply not feasible, while unsupervised inference is prone to noise, thus leaving the vast majority of these relations to be unreliable. To nevertheless find those relations which can be reliably utilized for learning, we follow a divide-and-conquer strategy: We… CONTINUE READING
    4 Citations
    Sharing Matters for Generalization in Deep Metric Learning
    • 5
    • PDF
    DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
    • 7
    • PDF
    PADS: Policy-Adapted Sampling for Visual Similarity Learning
    • 6
    • PDF
    Latent Space Conditioning on Generative Adversarial Networks
    • PDF


    Representation Learning by Learning to Count
    • 178
    • PDF
    Unsupervised Representation Learning by Predicting Image Rotations
    • 722
    • PDF
    Deep unsupervised learning of visual similarities
    • 24
    • Highly Influential
    • PDF
    Transitive Invariance for Self-Supervised Visual Representation Learning
    • 115
    • PDF
    Unsupervised Learning of Discriminative Attributes and Visual Representations
    • 75
    • Highly Influential
    • PDF
    Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
    • 287
    • Highly Influential
    • PDF
    Combining local and global: Rich and robust feature pooling for visual recognition
    • 25
    Unsupervised feature learning with C-SVDDNet
    • 21
    • PDF
    Binary Partition Tree construction from multiple features for image segmentation
    • 15
    Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
    • 811
    • Highly Influential
    • PDF