Concepedia

Saliency-based Pruning

Saliency-Based Pruning is a model compression technique that belongs to the class of structured or unstructured pruning methods, distinguished by its use of gradient-based sensitivity scores to identify and remove the least important parameters in a neural network according to their contribution to the loss function.

16

Publications

1.3K

Citations

52

Authors

22

Institutions

Publications per year

2017–2026

9

Parents

Publications

16

SNIP: Single-shot Network Pruning based on Connection Sensitivity

Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr · arXiv (Cornell University) · 2018 · 364 citations · Full text

, , +14

SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY

Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr · Oxford University Research Archive (ORA) (University of Oxford) · 2018 · 274 citations · Full text

, , +14

Accelerating Convolutional Networks via Global & Dynamic Filter Pruning

Shaohui Lin, Rongrong Ji, Yuchao Li et al. · 2018 · 224 citations · Full text

, , +13

On the Kalman filtering method in neural network training and pruning

John Sum, Chi-Sing Leung, Gilbert H. Young et al. · IEEE Transactions on Neural Networks · 1999 · 84 citations

, , +16

Input variable selection for neural networks: application to predicting the U.S. business cycle

Joachim Utans, John Moody, Steven Rehfuss et al. · 2002 · 62 citations

, , +15

1–5 of 16

Authors

52

  1. PH
    Philip H. S. Torr

    University of Oxford, United Kingdom

    3 publications · 657 citations

    3

    h-index

  2. TA
    Thalaiyasingam Ajanthan

    Australian National University, Australia

    3 publications · 657 citations

    3

    h-index

  3. NL
    Namhoon Lee

    Anyang University, South Korea

    3 publications · 657 citations

    3

    h-index

  4. BZ
    Baochang Zhang

    Beihang University, China

    1 publications · 224 citations

    1

    h-index

  5. SJ
    Stephen Jay Gould

    Harvard University, United States

    1 publications · 19 citations

    1

    h-index

1–5 of 52

Institutions

22

  1. University of Oxford

    Oxford, United Kingdom

    2 h-index

    6 publications

    1.9K citations

  2. Nanyang Technological University

    Singapore, Singapore

    1 h-index

    1 publications

    84 citations

  3. Chinese University of Hong Kong

    Hong Kong, Hong Kong

    1 h-index

    1 publications

    84 citations

  4. KLE Technological University

    Hubballi, India

    1 h-index

    8 publications

    112 citations

  5. Technion – Israel Institute of Technology

    Haifa, Israel

    1 h-index

    1 publications

    62 citations

  6. University of Haifa

    Haifa, Israel

    1 h-index

    1 publications

    23 citations

  7. Shenzhen University

    Shenzhen, China

    1 h-index

    2 publications

    36 citations

  8. Xiamen University

    Xiamen, China

    1 h-index

    4 publications

    896 citations

1–8 of 22

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 406 citations

    3

    h-index

  2. Oxford University Research Archive (ORA) (University of Oxford)

    Repository · 2 publications · 307 citations

    2

    h-index

  3. IEEE Transactions on Neural Networks

    2 publications · 123 citations

    2

    h-index

  4. Neural Information Processing Systems

    Conference · 1 publications · 10 citations

    1

    h-index

  5. 1

    h-index

1–5