Reconstruction Loss

Reconstruction Loss is a type of loss function used in machine learning that quantifies the discrepancy between the original input data and its reconstructed version, typically in models designed for dimensionality reduction or generative tasks, to enforce fidelity in the reproduction of data.

438

Publications

31.6K

Citations

1.8K

Authors

504

Institutions

Publications per year

2017–2026

412

Authors

1.8K

  1. LM
    Lin Ma

    Tencent (China), China

    4 publications · 504 citations

    4

    h-index

  2. QT
    Qiaoyu Tan

    Texas A&M University, United States

    4 publications · 189 citations

    4

    h-index

  3. NL
    Ninghao Liu

    Texas A&M University, United States

    4 publications · 189 citations

    4

    h-index

  4. MW
    Meng Wang

    Hefei University of Technology, China

    4 publications · 177 citations

    4

    h-index

  5. AY
    Alan Yuille

    Johns Hopkins University, United States

    4 publications · 126 citations

    4

    h-index

1–5 of 1.8K

Venues

  1. arXiv (Cornell University)

    Repository · 67 publications · 3.9K citations

    31

    h-index

  2. 19

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 14 publications · 890 citations

    14

    h-index

  4. IEEE Transactions on Image Processing

    14 publications · 863 citations

    13

    h-index

  5. IEEE Access

    13 publications · 357 citations

    12

    h-index

1–5