Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks

• URL: http://arxiv.org/abs/2402.07200v1
• Date: Sun, 11 Feb 2024 13:26:40 GMT
• Title: Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks
• Authors: Muqun Niu, Yuan Ren, Boyu Li and Chenchen Ding
• Abstract summary: We propose an operator-level improvement for training called Outlier Aware Batch Normalization (OABN) We also develop a clustering-based non-uniform quantization framework for Quantization-Aware Training (QAT) named ClusterQAT.
• Score: 7.446898033580747
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and inference, a structural re-parameterized (SR) network such as the representative RepVGG revitalizes the simple VGG-like network with a high accuracy comparable to advanced and often more complicated networks. However, the merging process in SR networks introduces outliers into weights, making their distribution distinct from conventional networks and thus heightening difficulties in quantization. To address this, we propose an operator-level improvement for training called Outlier Aware Batch Normalization (OABN). Additionally, to meet the demands of limited bitwidths while upkeeping the inference accuracy, we develop a clustering-based non-uniform quantization framework for Quantization-Aware Training (QAT) named ClusterQAT. Integrating OABN with ClusterQAT, the quantized performance of RepVGG is largely enhanced, particularly when the bitwidth falls below 8.

Related papers

• Online Training and Pruning of Deep Reinforcement Learning Networks [0.0]
  Scaling deep neural networks (NN) of reinforcement learning (RL) algorithms has been shown to enhance performance when feature extraction networks are used.<n>We propose an approach to integrate simultaneous training and pruning within advanced RL methods.
  arXiv  Detail & Related papers  (2025-07-16T07:17:41Z)
• Histogram-Equalized Quantization for logic-gated Residual Neural Networks [2.7036595757881323]
  Histogram-Equalized Quantization (HEQ) is an adaptive framework for linear symmetric quantization. HEQ automatically adapts the quantization thresholds using a unique step size optimization. Experiments on the STL-10 dataset even show that HEQ enables a proper training of our proposed logic-gated (OR, MUX) residual networks.
  arXiv  Detail & Related papers  (2025-01-08T14:06:07Z)
• Constraint Guided Model Quantization of Neural Networks [0.0]
  Constraint Guided Model Quantization (CGMQ) is a quantization aware training algorithm that uses an upper bound on the computational resources and reduces the bit-widths of the parameters of the neural network.<n>It is shown on MNIST and CIFAR10 that the performance of CGMQ is competitive with state-of-the-art quantization aware training algorithms.
  arXiv  Detail & Related papers  (2024-09-30T09:41:16Z)
• RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization [14.447148108341688]
  We propose efficient unsupervised domain adaptation with ReTraining-Free Quantization (RTF-Q) Our approach uses low-precision quantization architectures with varying computational costs, adapting to devices with dynamic budgets. We demonstrate that our network achieves competitive accuracy with state-of-the-art methods across three benchmarks.
  arXiv  Detail & Related papers  (2024-08-11T11:53:29Z)
• An Enhanced Encoder-Decoder Network Architecture for Reducing Information Loss in Image Semantic Segmentation [6.596361762662328]
  We introduce an innovative encoder-decoder network structure enhanced with residual connections. Our approach employs a multi-residual connection strategy designed to preserve the intricate details across various image scales more effectively. To enhance the convergence rate of network training and mitigate sample imbalance issues, we have devised a modified cross-entropy loss function.
  arXiv  Detail & Related papers  (2024-05-26T05:15:53Z)
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• Split-Boost Neural Networks [1.1549572298362787]
  We propose an innovative training strategy for feed-forward architectures - called split-boost. Such a novel approach ultimately allows us to avoid explicitly modeling the regularization term. The proposed strategy is tested on a real-world (anonymized) dataset within a benchmark medical insurance design problem.
  arXiv  Detail & Related papers  (2023-09-06T17:08:57Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Vertical Layering of Quantized Neural Networks for Heterogeneous Inference [57.42762335081385]
  We study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. We can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model.
  arXiv  Detail & Related papers  (2022-12-10T15:57:38Z)
• Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks [58.195261590442406]
  We study the problem of training and certifying adversarially robust quantized neural networks (QNNs) Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization. We present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs.
  arXiv  Detail & Related papers  (2022-11-29T13:32:38Z)
• Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric Quantizer [1.9659095632676098]
  Quantizing weights and activations of deep neural networks is essential for deploying them in resource-constrained devices or cloud platforms. While binarization is a special case of quantization, this extreme case often leads to several training difficulties. We develop a unified quantization framework, denoted as UniQ, to overcome binarization difficulties.
  arXiv  Detail & Related papers  (2021-04-01T02:33:31Z)
• Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations [12.716429755564821]
  Deep-predictive-coding networks (DPCNs) are hierarchical, generative models that rely on feed-forward and feed-back connections. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse states of a dynamic model. We propose an optimization strategy, with better empirical and theoretical convergence, based on accelerated proximal gradients.
  arXiv  Detail & Related papers  (2021-01-18T02:30:13Z)
• Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search [112.05977301976613]
  We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
  arXiv  Detail & Related papers  (2020-10-09T03:52:16Z)
• Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution [79.97180849505294]
  We propose a novel coupled unmixing network with a cross-attention mechanism, CUCaNet, to enhance the spatial resolution of HSI. Experiments are conducted on three widely-used HS-MS datasets in comparison with state-of-the-art HSI-SR models.
  arXiv  Detail & Related papers  (2020-07-10T08:08:20Z)

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.