paper-with-me

Papers

QKD: Quantization-aware Knowledge Distillation

2019-11-28 · Jangho Kim, Yash Bhalgat, Jinwon Lee, Chirag Patel, Nojun Kwak

Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is quite promising to meet these requirements, it may not work as desired. It is mainly because the regularization effect of KD further diminishes the already reduced representation power of a quantized model. To address this short-coming, we propose Quantization-aware Knowledge Distillation (QKD) wherein quantization and KD are care-fully coordinated in three phases. First, Self-studying (SS) phase fine-tunes a quantized low-precision student network without KD to obtain a good initialization. Second, Co-studying (CS) phase tries to train a teacher to make it more quantizaion-friendly and powerful than a fixed teacher. Finally, Tutoring (TU) phase transfers knowledge from the trained teacher to the student. We extensively evaluate our method on ImageNet and CIFAR-10/100 datasets and show an ablation study on networks with both standard and depthwise-separable convolutions. The proposed QKD outperformed existing state-of-the-art methods (e.g., 1.3% improvement on ResNet-18 with W4A4, 2.6% on MobileNetV2 with W4A4). Additionally, QKD could recover the full-precision accuracy at as low as W3A3 quantization on ResNet and W6A6 quantization on MobilenetV2.

📄 PDF Abstract BibTeX arXiv:1911.12491

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationQuantization

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

Self-Supervised Quantization-Aware Knowledge Distillation

2024-03-17 · Kaiqi Zhao, Ming Zhao

Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. However, existing works applying KD to QAT require tedious hyper…

Knowledge DistillationQuantization

Poster: Self-Supervised Quantization-Aware Knowledge Distillation

2023-09-22 · Kaiqi Zhao, Ming Zhao

Quantization-aware training (QAT) starts with a pre-trained full-precision model and performs quantization during retraining. However, existing QAT works require supervision from the labels and they suffer from accuracy …

Knowledge DistillationQuantization

Quantized Feature Distillation for Network Quantization

2023-07-20 · Ke Zhu, Yin-Yin He, Jianxin Wu

Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid gro…

image-classificationImage ClassificationImage SegmentationKnowledge Distillation+5

Data-Augmented Quantization-Aware Knowledge Distillation

2025-09-04 · Justin Kur, Kaiqi Zhao arxiv

Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. Existing KD and QAT works focus on improving the accuracy of qua…

Knowledge DistillationData Augmentation

Decoder-Free Distillation for Quantized Image Restoration

2026-03-10 · S. M. A. Sharif, Abdur Rehman, Seongwan Kim, Jaeho Lee arxiv

Quantization-Aware Training (QAT), combined with Knowledge Distillation (KD), holds immense promise for compressing models for edge deployment. However, joint optimization for precision-sensitive image restoration (IR) t…

Knowledge DistillationImage RestorationObject Detection