Related papers: Hard Sample Matters a Lot in Zero-Shot Quantizatio…
Model quantization is a promising approach to compress deep neural networks and accelerate inference, making it possible to be deployed on mobile and edge devices. To retain the high performance of full-precision models, most existing…
How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and…
Network quantization has proven to be a powerful approach to reduce the memory and computational demands of deep learning models for deployment on resource-constrained devices. However, traditional quantization methods often rely on access…
Quantization is a key technique to reduce network size and computational complexity by representing the network parameters with a lower precision. Traditional quantization methods rely on access to original training data, which is often…
Learning to synthesize data has emerged as a promising direction in zero-shot quantization (ZSQ), which represents neural networks by low-bit integer without accessing any of the real data. In this paper, we observe an interesting…
Zero-shot quantization (ZSQ) using synthetic data is a key approach for post-training quantization (PTQ) under privacy and security constraints. However, existing data generation methods often struggle to effectively generate data suitable…
Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers, in order to accelerate inference and reduce computation. Quantizing a model without access to the original data, zero-shot…
Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing…
Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recently, efforts have been afoot towards zero-shot quantization…
Zero-shot quantization (ZSQ) enables neural network compression without original training data, making it a promising solution for restricted data access scenarios. To compensate for the lack of data, recent ZSQ methods typically rely on…
Zero-shot quantization is a promising approach for developing lightweight deep neural networks when data is inaccessible owing to various reasons, including cost and issues related to privacy. By exploiting the learned parameters ($\mu$ and…
Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to security and privacy…
Model quantization is considered as a promising method to greatly reduce the resource requirements of deep neural networks. To deal with the performance drop induced by quantization errors, a popular method is to use training data to…
Quantization is a promising approach for reducing the inference time and memory footprint of neural networks. However, most existing quantization methods require access to the original training dataset for retraining during quantization.…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…
Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…
Transductive zero-shot learning (T-ZSL) which could alleviate the domain shift problem in existing ZSL works, has received much attention recently. However, an open problem in T-ZSL: how to effectively make use of unseen-class samples for…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…
Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge, i.e., visual and semantic relationships, obtained from seen classes, where image augmentation techniques are commonly applied to improve the…
Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…