Switchable-Precision Universally Slimmable Networks
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 3347-3351
Abstract
No abstract availableFunding Information
- NSTC (115-2221-E-A49-146)
This publication has 12 references indexed in Scilit:
- Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning2023
- Layer Pruning for Obtaining Shallower ResNetsIEEE Signal Processing Letters, 2022
- InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks2021
- AdaBits: Neural Network Quantization With Adaptive Bit-Widths2020
- Increasing Compactness of Deep Learning Based Speech Enhancement Models With Parameter Pruning and Quantization TechniquesIEEE Signal Processing Letters, 2019
- Universally Slimmable Networks and Improved Training Techniques2019
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- Identity Mappings in Deep Residual Networks2016
- ImageNet: A large-scale hierarchical image database2009