# ACQ: Improving Generative Data-free Quantization Via Attention Correction

arXiv: https://arxiv.org/abs/2301.07266 · HTML: https://mlsanity.com/paper/2301.07266/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 54 references that are in the map.
- First posted on arXiv 18 Jan 2023.

## Builds on (most cited first, 30 of 42)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2001.06937/) (2020)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [Grad-CAM: Why did you say that?](https://mlsanity.com/paper/1611.07450/) (2016)
- [Improving Neural Network Quantization without Retraining using Outlier Channel Splitting](https://mlsanity.com/paper/1901.09504/) (2019)
- [Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks](https://mlsanity.com/paper/1909.13144/) (2019)
- [Zero-shot Knowledge Transfer via Adversarial Belief Matching](https://mlsanity.com/paper/1905.09768/) (2019)
- [Overcoming Oscillations in Quantization-Aware Training](https://mlsanity.com/paper/2203.11086/) (2022)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [Degree-Quant: Quantization-Aware Training for Graph Neural Networks](https://mlsanity.com/paper/2008.05000/) (2020)
- [Generative Low-bitwidth Data Free Quantization](https://mlsanity.com/paper/2003.03603/) (2020)
- [Diversifying Sample Generation for Accurate Data-Free Quantization](https://mlsanity.com/paper/2103.01049/) (2021)
- [EasyQuant: Post-training Quantization via Scale Optimization](https://mlsanity.com/paper/2006.16669/) (2020)
- [Knowledge Distillation with Adversarial Samples Supporting Decision Boundary](https://mlsanity.com/paper/1805.05532/) (2018)
- [Zero-shot Adversarial Quantization](https://mlsanity.com/paper/2103.15263/) (2021)
- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [Post-training 4-bit quantization of convolution networks for rapid-deployment](https://mlsanity.com/paper/1810.05723/) (2018)

## Built on by (most cited first, 2 of 2)

- [MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization](https://mlsanity.com/paper/2305.08117/) (2023)
- [Data Generation for Hardware-Friendly Post-Training Quantization](https://mlsanity.com/paper/2410.22110/) (2024)

## Abstract (arXiv)

Data-free quantization aims to achieve model quantization without accessing any authentic sample. It is significant in an application-oriented context involving data privacy. Converting noise vectors into synthetic samples through a generator is a popular data-free quantization method, which is called generative data-free quantization. However, there is a difference in attention between synthetic samples and authentic samples. This is always ignored and restricts the quantization performance. First, since synthetic samples of the same class are prone to have homogenous attention, the quantized network can only learn limited modes of attention. Second, synthetic samples in eval mode and training mode exhibit different attention. Hence, the batch-normalization statistics matching tends to be inaccurate. ACQ is proposed in this paper to fix the attention of synthetic samples. An attention center position-condition generator is established regarding the homogenization of intra-class attention. Restricted by the attention center matching loss, the attention center position is treated as the generator's condition input to guide synthetic samples in obtaining diverse attention. Moreover, we design adversarial loss of paired synthetic samples under the same condition to prevent the generator from paying overmuch attention to the condition, which may result in mode collapse. To improve the attention similarity of synthetic samples in different network modes, we introduce a consistency penalty to guarantee accurate BN statistics matching. The experimental results demonstrate that ACQ effectively improves the attention problems of synthetic samples. Under various training settings, ACQ achieves the best quantization performance. For the 4-bit quantization of Resnet18 and Resnet50, ACQ reaches 67.55% and 72.23% accuracy, respectively.