A Data-Free Analytical Quantization Scheme for Deep Learning Models
This addresses storage and speed challenges for deploying models on devices like mobile or embedded systems, but appears incremental as it builds on existing quantization techniques.
The paper tackles the problem of deploying deep learning models on resource-constrained devices by introducing a post-training quantization method that reduces model size and computational requirements while preserving accuracy, with empirical results showing significant reductions.
Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices. Quantization is one technique that aims to alleviate these large storage requirements and speed up the inference process by reducing the precision of model parameters to lower-bit representations. In this paper, we introduce a novel post-training quantization method for model weights. Our method finds optimal clipping thresholds and scaling factors along with mathematical guarantees that our method minimizes quantization noise. Empirical results on real-world datasets demonstrate that our quantization scheme significantly reduces model size and computational requirements while preserving model accuracy.