Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

  title={Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings},
  author={P. Jacob and D. Picard and A. Histace and E. Klein},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  • P. Jacob, D. Picard, +1 author E. Klein
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Learning an effective similarity measure between image representations is key to the success of recent advances in visual search tasks (e.g. verification or zero-shot learning. [...] Key Method This regularizer enforces visually-close images to have deep features with the same distribution which are well localized in the feature space. We provide a theoretical analysis supporting this regularization effect. We also show the effectiveness of our approach by obtaining state-of-the-art results on 4 well-known…Expand Abstract
    16 Citations
    DIABLO: Dictionary-based Attention Block for Deep Metric Learning
    DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
    • 5
    • PDF
    Keypoint-Aligned Embeddings for Image Retrieval and Re-identification
    Proxy Anchor Loss for Deep Metric Learning
    • 11
    • PDF
    PADS: Policy-Adapted Sampling for Visual Similarity Learning
    • 5
    • PDF
    Distance Metric Learning with Joint Representation Diversification
    Deep Metric Learning with Alternating Projections onto Feasible Sets
    Diversified Mutual Learning for Deep Metric Learning


    Deep Metric Learning with Angular Loss
    • 196
    • PDF
    Deep Variational Metric Learning
    • 40
    • Highly Influential
    • PDF
    Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly
    • 63
    • PDF
    Metric Learning with Adaptive Density Discrimination
    • 125
    • PDF
    Deep Metric Learning via Facility Location
    • 190
    • PDF
    Attention-based Ensemble for Deep Metric Learning
    • 92
    • Highly Influential
    • PDF
    BIER — Boosting Independent Embeddings Robustly
    • 72
    • PDF
    Deep Metric Learning with Hierarchical Triplet Loss
    • 122
    • Highly Influential
    • PDF
    Learning Deep Embeddings with Histogram Loss
    • 211
    • PDF
    Improved Deep Metric Learning with Multi-class N-pair Loss Objective
    • 512
    • PDF