IEEE Internet of Things Journal · 2024 · 14 citations · 22 references
ComputingComputer ScienceInformation TechnologyFeature EngineeringInternet Of ThingsSensorsIot Application DevelopmentIot Data AcquisitionIot Embedded SystemsIot SensorsSensor NetworksWireless Sensor NetworksAdaptive HintsBit-width OptimizationFeature QuantizationIot Data ProcessingQuantization
Quantization has enabled the widespread implementation of deep learning algorithms on resource-constrained Internet of Things (IoT) devices, which compresses neural networks by reducing the bit-width of their parameters. However, most quantization methods invade privacy as they require real training datasets for calibration or fine-tuning. As a solution, zero-shot quantization (ZSQ) has emerged as a paradigm to quantize neural networks without accessing training datasets. Most employ data generation schemes to synthesize calibration data for knowledge transfer from the full-precision networks to the quantized ones. For privacy-protected and resource-constrained IoT devices, achieving optimal deployment necessitates the strategic integration of synthetic data generation and low-bit-width quantization techniques. However, when it comes to the lower bit-width case in ZSQ, we observe that the discrepancy between the full-precision network and the quantized network tends to widen significantly, hindering the knowledge transfer, which is attributed to the three following challenges: 1) hard logits matching with wide discrepancy; 2) unstable feature alignment with huge quantization error; and 3) synthetic data with low diversity. To address these issues, this article presents S-ZSQ, a novel ZSQ framework with two-pronged strategies that enhances both knowledge transfer and synthetic data generation, which enables low-bit-width quantized network to derive more soft feature-infused hints from the full-precision network. We achieve significant improvements on classification tasks, including CIFAR-10/100 and ImageNet-1k, with fewer fine-tuning epochs, particularly in scenarios involving low-bit-width quantization. For example, in the 3-bit ResNet-18/ResNet-50 case, we outperform AdaDFQ by 8.08%/11.16% in top-1 accuracy on ImageNet-1k.
22
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Laurens van der Maaten et al. · 2017 · 44.7K citations
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky, Jia Deng, Hao Su et al. · International Journal of Computer Vision · 2015 · 40.2K citations
On Information and Sufficiency
S. Kullback, R. A. Leibler · The Annals of Mathematical Statistics · 1951 · 20K citations · Full text
Sergey Zagoruyko, Nikos Komodakis · 2016 · 6K citations