Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

• URL: http://arxiv.org/abs/2111.02625v1
• Date: Thu, 4 Nov 2021 04:52:50 GMT
• Title: Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
• Authors: Kanghyun Choi, Deokki Hong, Noseong Park, Youngsok Kim, Jinho Lee
• Abstract summary: We propose Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples. The experimental results show that Qimera achieves state-of-the-art performances for various settings on data-free quantization.
• Score: 8.975667614727652
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original training data to maintain the accuracy of the full-precision models, which is often infeasible in real-world scenarios for security and privacy issues. A popular approach to perform quantization without access to the original data is to use synthetically generated samples, based on batch-normalization statistics or adversarial learning. However, the drawback of such approaches is that they primarily rely on random noise input to the generator to attain diversity of the synthetic samples. We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries. To this end, we propose Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples. For the superposed embeddings to better reflect the original distribution, we also propose using an additional disentanglement mapping layer and extracting information from the full-precision model. The experimental results show that Qimera achieves state-of-the-art performances for various settings on data-free quantization. Code is available at https://github.com/iamkanghyunchoi/qimera.

Related papers

• Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning [20.413801240717646]
  We propose a data-free mixed-precision compensation (DF-MPC) method to recover the performance of an ultra-low precision quantized model without any data and fine-tuning process. Our DF-MPC is able to achieve higher accuracy for an ultra-low precision quantized model compared to the recent methods without any data and fine-tuning process.
  arXiv  Detail & Related papers  (2023-07-02T07:16:29Z)
• Post-training Model Quantization Using GANs for Synthetic Data Generation [57.40733249681334]
  We investigate the use of synthetic data as a substitute for the calibration with real data for the quantization method. We compare the performance of models quantized using data generated by StyleGAN2-ADA and our pre-trained DiStyleGAN, with quantization using real data and an alternative data generation method based on fractal images.
  arXiv  Detail & Related papers  (2023-05-10T11:10:09Z)
• ClusterQ: Semantic Feature Distribution Alignment for Data-Free Quantization [111.12063632743013]
  We propose a new and effective data-free quantization method termed ClusterQ. To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics. We also incorporate the intra-class variance to solve class-wise mode collapse.
  arXiv  Detail & Related papers  (2022-04-30T06:58:56Z)
• Learning Summary Statistics for Bayesian Inference with Autoencoders [58.720142291102135]
  We use the inner dimension of deep neural network based Autoencoders as summary statistics. To create an incentive for the encoder to encode all the parameter-related information but not the noise, we give the decoder access to explicit or implicit information that has been used to generate the training data.
  arXiv  Detail & Related papers  (2022-01-28T12:00:31Z)
• Conditional Variational Autoencoder for Learned Image Reconstruction [5.487951901731039]
  We develop a novel framework that approximates the posterior distribution of the unknown image at each query observation. It handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned reconstructive properties are transferable between different datasets.
  arXiv  Detail & Related papers  (2021-10-22T10:02:48Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• Zero-shot Adversarial Quantization [11.722728148523366]
  We propose a zero-shot adversarial quantization (ZAQ) framework, facilitating effective discrepancy estimation and knowledge transfer. This is achieved by a novel two-level discrepancy modeling to drive a generator to synthesize informative and diverse data examples. We conduct extensive experiments on three fundamental vision tasks, demonstrating the superiority of ZAQ over the strong zero-shot baselines.
  arXiv  Detail & Related papers  (2021-03-29T01:33:34Z)
• Contextual Dropout: An Efficient Sample-Dependent Dropout Module [60.63525456640462]
  Dropout has been demonstrated as a simple and effective module to regularize the training process of deep neural networks. We propose contextual dropout with an efficient structural design as a simple and scalable sample-dependent dropout module. Our experimental results show that the proposed method outperforms baseline methods in terms of both accuracy and quality of uncertainty estimation.
  arXiv  Detail & Related papers  (2021-03-06T19:30:32Z)
• Oops I Took A Gradient: Scalable Sampling for Discrete Distributions [53.3142984019796]
  We show that this approach outperforms generic samplers in a number of difficult settings. We also demonstrate the use of our improved sampler for training deep energy-based models on high dimensional discrete data.
  arXiv  Detail & Related papers  (2021-02-08T20:08:50Z)
• Generative Low-bitwidth Data Free Quantization [44.613912463011545]
  We propose Generative Low-bitwidth Data Free Quantization (GDFQ) to remove the data dependence burden. With the help of generated data, we can quantize a model by learning knowledge from the pre-trained model. Our method achieves much higher accuracy on 4-bit quantization than the existing data free quantization method.
  arXiv  Detail & Related papers  (2020-03-07T16:38:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.