HTQ: Exploring the High-Dimensional Trade-Off of mixed-precision quantization
- 15 July 2024
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 156
Abstract
No abstract availableKeywords
Funding Information
- National Major Science and Technology Projects of China
- National Natural Science Foundation of China
This publication has 22 references indexed in Scilit:
- MetaMix: Meta-State Precision Searcher for Mixed-Precision Activation QuantizationProceedings of the AAAI Conference on Artificial Intelligence, 2024
- RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers2023
- I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference2023
- Mixed-precision quantized neural networks with progressively decreasing bitwidthPattern Recognition, 2021
- Binary neural networks: A surveyPattern Recognition, 2020
- Deep learningNature, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrixJournal of the ACM, 2011
- Optimal bit allocation via the generalized BFOS algorithmIEEE Transactions on Information Theory, 1991
- Efficient bit allocation for an arbitrary set of quantizers (speech coding)IEEE Transactions on Acoustics, Speech, and Signal Processing, 1988