Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization
Data-free quantization is a task that compresses the neural network to low bit-width without access to original training data. Most existing data-free quantization methods cause severe performance degradation due to inaccurate activation clipping range and quantization error, especially for low bit-width. In this paper, we present a simple yet effective data-free quantization method with accurate activation clipping and adaptive batch normalization. Accurate activation clipping (AAC) improves the model accuracy by exploiting accurate activation information from the full-precision model. Adaptive batch normalization firstly proposes to address the quantization error from distribution changes by updating the batch normalization layer adaptively. Extensive experiments demonstrate that the proposed data-free quantization method can yield surprisingly performance, achieving 64.33% top-1 accuracy of ResNet18 on ImageNet dataset, with 3.7% absolute improvement outperforming the existing state-of-the-art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Data Free QuantizationQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PACT: Parameterized Clipping Activation for Quantized Neural Networks
Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. To address this cost, a number of quantization schemes have been proposed - but most of these techniques focus…
QuantizationBridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)
Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. In order to reduce this cost, several quantization schemes have gained attention recently with some focusing o…
General ClassificationQuantizationACIQ: Analytical Clipping for Integer Quantization of neural networks
We analyze the trade-off between quantization noise and clipping distortion in low precision networks. We identify the statistics of various tensors, and derive exact expressions for the mean-square-error degradation due…
QuantizationBASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks
In this paper, we propose Branch-wise Activation-clipping Search Quantization (BASQ), which is a novel quantization method for low-bit activation. BASQ optimizes clip value in continuous search space while simultaneously…
Neural Architecture SearchQuantizationOmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Large language models (LLMs) have revolutionized natural language processing tasks. However, their practical deployment is hindered by their immense memory and computation requirements. Although recent post-training quan…
Common Sense ReasoningComputational EfficiencyGPULarge Language Model+2