Sharing Matters for Generalization in Deep Metric Learning

@article{Milbich2020SharingMF,
  title={Sharing Matters for Generalization in Deep Metric Learning},
  author={Timo Milbich and Karsten Roth and B. Brattoli and B. Ommer},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  year={2020},
  volume={PP}
}
Learning the similarity between images constitutes the foundation for numerous vision tasks. The common paradigm is discriminative metric learning, which seeks an embedding that separates different training classes. However, the main challenge is to learn a metric that not only generalizes from training to novel, but related, test samples. It should also transfer to different object classes. So what complementary information is missed by the discriminative paradigm? Besides finding… Expand
5 Citations

References

SHOWING 1-10 OF 44 REFERENCES
MIC: Mining Interclass Characteristics for Improved Metric Learning
  • 29
  • Highly Influential
  • PDF
Deep Variational Metric Learning
  • 43
  • Highly Influential
  • PDF
Deep Metric Learning via Lifted Structured Feature Embedding
  • 586
  • Highly Influential
  • PDF
Divide and Conquer the Embedding Space for Metric Learning
  • 42
  • PDF
Ranked List Loss for Deep Metric Learning
  • 71
  • PDF
Improved Deep Metric Learning with Multi-class N-pair Loss Objective
  • 650
  • Highly Influential
  • PDF
Sampling Matters in Deep Embedding Learning
  • 416
  • Highly Influential
  • PDF
Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly
  • 77
  • PDF
An Adversarial Approach to Hard Triplet Generation
  • 54
  • PDF
...
1
2
3
4
5
...