AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks
DOI:
https://doi.org/10.1609/aaai.v35i3.16350Keywords:
Image and Video RetrievalAbstract
Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that lower-level layers extract general features and higher-level layers extract specific features. Based on our discussion, we propose an algorithm that improves fine-tuning performance and reduces network complexity through layer-wise pruning and auto-tuning of layer-wise learning rates. The proposed algorithm has verified the effectiveness by achieving state-of-the-art performance on the image retrieval benchmark datasets (CUB-200, Cars-196, Stanford online product, and Inshop). Code is available at https://github.com/youngminPIL/AutoLR.Downloads
Published
2021-05-18
How to Cite
Ro, Y., & Choi, J. Y. (2021). AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2486-2494. https://doi.org/10.1609/aaai.v35i3.16350
Issue
Section
AAAI Technical Track on Computer Vision II