Triplet Loss

Triplet Loss is a loss function in metric learning that penalizes the relative distance between an anchor sample, a positive sample of the same class, and a negative sample of a different class by enforcing a margin-based separation in the embedding space.

614

Publications

45K

Citations

2.1K

Authors

580

Institutions

Publications per year

2017–2026

563

Authors

2.1K

  1. SS
    Shiguang Shan

    Institute of Computing Technology, China

    6 publications · 504 citations

    6

    h-index

  2. AM
    Aythami Morales

    Universidad Autónoma de Madrid, Spain

    6 publications · 293 citations

    6

    h-index

  3. WZ
    Wei‐Shi Zheng

    Sun Yat-sen University, China

    4 publications · 231 citations

    4

    h-index

  4. XC
    Xilin Chen

    Institute of Computing Technology, China

    4 publications · 454 citations

    4

    h-index

  5. HL
    Hanjiang Lai

    Sun Yat-sen University, China

    4 publications · 110 citations

    4

    h-index

1–5 of 2.1K

Venues

  1. arXiv (Cornell University)

    Repository · 55 publications · 6.2K citations

    24

    h-index

  2. 18

    h-index

  3. IEEE Transactions on Multimedia

    18 publications · 1.3K citations

    17

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 16 publications · 849 citations

    15

    h-index

  5. IEEE Transactions on Image Processing

    15 publications · 990 citations

    14

    h-index

1–5