Hard Sample Matters a Lot in Zero-Shot Quantization

• URL: http://arxiv.org/abs/2303.13826v1
• Date: Fri, 24 Mar 2023 06:22:57 GMT
• Title: Hard Sample Matters a Lot in Zero-Shot Quantization
• Authors: Huantong Li, Xiangmiao Wu, Fanbing Lv, Daihai Liao, Thomas H. Li, Yonggang Zhang, Bo Han, Mingkui Tan
• Abstract summary: Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the performance of quantized models depends heavily on the quality of synthetic samples. We propose HArd sample Synthesizing and Training (HAST) to address this issue.
• Score: 52.32914196337281
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the performance of quantized models depends heavily on the quality of synthetic samples. Nonetheless, we find that the synthetic samples constructed in existing ZSQ methods can be easily fitted by models. Accordingly, quantized models obtained by these methods suffer from significant performance degradation on hard samples. To address this issue, we propose HArd sample Synthesizing and Training (HAST). Specifically, HAST pays more attention to hard samples when synthesizing samples and makes synthetic samples hard to fit when training quantized models. HAST aligns features extracted by full-precision and quantized models to ensure the similarity between features extracted by these two models. Extensive experiments show that HAST significantly outperforms existing ZSQ methods, achieving performance comparable to models that are quantized with real data.

Related papers

• One Step Diffusion via Shortcut Models [109.72495454280627]
  We introduce shortcut models, a family of generative models that use a single network and training phase to produce high-quality samples. Shortcut models condition the network on the current noise level and also on the desired step size, allowing the model to skip ahead in the generation process. Compared to distillation, shortcut models reduce complexity to a single network and training phase and additionally allow varying step budgets at inference time.
  arXiv  Detail & Related papers  (2024-10-16T13:34:40Z)
• Provable Statistical Rates for Consistency Diffusion Models [87.28777947976573]
  Despite the state-of-the-art performance, diffusion models are known for their slow sample generation due to the extensive number of steps involved. This paper contributes towards the first statistical theory for consistency models, formulating their training as a distribution discrepancy minimization problem.
  arXiv  Detail & Related papers  (2024-06-23T20:34:18Z)
• Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss [4.877532217193618]
  Existing quantization techniques rely heavily on experience and "fine-tuning" skills. This study provides a methodology for acquiring a mixed-precise quantization model with a lower loss than the full precision model. In particular, we will demonstrate that neural networks with massive identity mappings are resistant to the quantization method.
  arXiv  Detail & Related papers  (2022-07-20T10:55:34Z)
• 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)
• Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis [20.34562156468408]
  We propose a non-generative model to address these problems. In addition, we formulate a new ZSL task named the 'Few-shot Seen class and Zero-shot Unseen class learning' (FSZU)
  arXiv  Detail & Related papers  (2022-03-10T12:32:26Z)
• Diverse Sample Generation: Pushing the Limit of Data-free Quantization [85.95032037447454]
  This paper presents a generic Diverse Sample Generation scheme for the generative data-free post-training quantization and quantization-aware training. For large-scale image classification tasks, our DSG can consistently outperform existing data-free quantization methods.
  arXiv  Detail & Related papers  (2021-09-01T07:06:44Z)
• Closed-form Continuous-Depth Models [99.40335716948101]
  Continuous-depth neural models rely on advanced numerical differential equation solvers. We present a new family of models, termed Closed-form Continuous-depth (CfC) networks, that are simple to describe and at least one order of magnitude faster.
  arXiv  Detail & Related papers  (2021-06-25T22:08:51Z)
• Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics [14.704630929165274]
  We study the problem of reconstructing binary graphical models from correlated samples produced by a dynamical process. We analyze the sample complexity of two estimators that are based on the interaction screening objective and the conditional likelihood loss.
  arXiv  Detail & Related papers  (2021-04-02T11:44:13Z)
• 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)

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.