Search Results for author:
Found 9 papers, 0 papers with code
How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training
This paper investigates three different parameterizations of asymmetric uniform quantization for quantization-aware training: (1) scale and offset, (2) minimum and maximum, and (3) beta and gamma.
DONNAv2 -- Lightweight Neural Architecture Search for Vision tasks
Here, we have developed an elegant approach to eliminate building the accuracy predictor and extend DONNA to a computationally efficient setting.
Softmax Bias Correction for Quantized Generative Models
Post-training quantization (PTQ) is the go-to compression technique for large generative models, such as stable diffusion or large language models.
Speaker Diaphragm Excursion Prediction: deep attention and online adaptation
Speaker protection algorithm is to leverage the playback signal properties to prevent over excursion while maintaining maximum loudness, especially for the mobile phone with tiny loudspeakers.
FP8 versus INT8 for efficient deep learning inference
We theoretically show the difference between the INT and FP formats for neural networks and present a plethora of post-training quantization and quantization-aware-training results to show how this theory translates to practice.
A Practical Mixed Precision Algorithm for Post-Training Quantization
We experimentally validate our proposed method on several computer vision tasks, natural language processing tasks and many different networks, and show that we can find mixed precision networks that provide a better trade-off between accuracy and efficiency than their homogeneous bit-width equivalents.
Hand gesture recognition using 802.11ad mmWave sensor in the mobile device
Range-Doppler information (RDI) is obtained by using pulse Doppler radar for gesture recognition.
Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)
chapter 4) and quantization-aware training (QAT, cf.
QKD: Quantization-aware Knowledge Distillation
First, Self-studying (SS) phase fine-tunes a quantized low-precision student network without KD to obtain a good initialization.
