Learnable Companding Quantization for Accurate Low-bit Neural Networks
- URL: http://arxiv.org/abs/2103.07156v1
- Date: Fri, 12 Mar 2021 09:06:52 GMT
- Title: Learnable Companding Quantization for Accurate Low-bit Neural Networks
- Authors: Kohei Yamamoto
- Abstract summary: Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed.
It is still hard for extremely low-bit models to achieve accuracy comparable with that of full-precision models.
We propose learnable companding quantization (LCQ) as a novel non-uniform quantization method for 2-, 3-, and 4-bit models.
- Score: 3.655021726150368
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Quantizing deep neural networks is an effective method for reducing memory
consumption and improving inference speed, and is thus useful for
implementation in resource-constrained devices. However, it is still hard for
extremely low-bit models to achieve accuracy comparable with that of
full-precision models. To address this issue, we propose learnable companding
quantization (LCQ) as a novel non-uniform quantization method for 2-, 3-, and
4-bit models. LCQ jointly optimizes model weights and learnable companding
functions that can flexibly and non-uniformly control the quantization levels
of weights and activations. We also present a new weight normalization
technique that allows more stable training for quantization. Experimental
results show that LCQ outperforms conventional state-of-the-art methods and
narrows the gap between quantized and full-precision models for image
classification and object detection tasks. Notably, the 2-bit ResNet-50 model
on ImageNet achieves top-1 accuracy of 75.1% and reduces the gap to 1.7%,
allowing LCQ to further exploit the potential of non-uniform quantization.
Related papers
- 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution [83.09117439860607]
Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment.
It is notorious that low-bit quantization degrades the accuracy of SR models compared to their full-precision (FP) counterparts.
We present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization.
arXiv Detail & Related papers (2024-06-10T06:06:11Z) - FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search [50.07268323597872]
We propose the first one-shot mixed-precision quantization search that eliminates the need for retraining in both integer and low-precision floating point models.
With integer models, we increase the accuracy of ResNet-18 on ImageNet by 1.31% and ResNet-50 by 0.90% with equivalent model cost over previous methods.
For the first time, we explore a novel mixed-precision floating-point search and improve MobileNetV2 by up to 0.98% compared to prior state-of-the-art FP8 models.
arXiv Detail & Related papers (2023-08-07T04:17:19Z) - Mixed Precision Post Training Quantization of Neural Networks with
Sensitivity Guided Search [7.392278887917975]
Mixed-precision quantization allows different tensors to be quantized to varying levels of numerical precision.
We evaluate our method for computer vision and natural language processing and demonstrate latency reductions of up to 27.59% and 34.31%.
arXiv Detail & Related papers (2023-02-02T19:30:00Z) - Analysis of Quantization on MLP-based Vision Models [36.510879540365636]
Quantization is taken as a model compression technique, which obtains efficient models by converting floating-point weights and activations in the neural network into lower-bit integers.
We show in the paper that directly applying quantization to bounded-based models will lead to significant accuracy.
arXiv Detail & Related papers (2022-09-14T02:55:57Z) - BiTAT: Neural Network Binarization with Task-dependent Aggregated
Transformation [116.26521375592759]
Quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation.
Extreme quantization (1-bit weight/1-bit activations) of compactly-designed backbone architectures results in severe performance degeneration.
This paper proposes a novel Quantization-Aware Training (QAT) method that can effectively alleviate performance degeneration.
arXiv Detail & Related papers (2022-07-04T13:25:49Z) - CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple
Quantization Steps [1.3106063755117399]
This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs)
By using better training ability of the accurate model in an iterative manner, the proposed method can produce enhanced trained weights for the low-bit quantized model in each cycle.
Notably, the training method can advance Top-1 and Top-5 accuracies of the binarized ResNet-18 on the ImageNet dataset by 5.80% and 6.85%, respectively.
arXiv Detail & Related papers (2022-06-26T05:54:12Z) - One Model for All Quantization: A Quantized Network Supporting Hot-Swap
Bit-Width Adjustment [36.75157407486302]
We propose a method to train a model for all quantization that supports diverse bit-widths.
We use wavelet decomposition and reconstruction to increase the diversity of weights.
Our method can achieve accuracy comparable to dedicated models trained at the same precision.
arXiv Detail & Related papers (2021-05-04T08:10:50Z) - Direct Quantization for Training Highly Accurate Low Bit-width Deep
Neural Networks [73.29587731448345]
This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations.
First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights.
Second, to obtain low bit-width activations, existing works consider all channels equally.
arXiv Detail & Related papers (2020-12-26T15:21:18Z) - DAQ: Distribution-Aware Quantization for Deep Image Super-Resolution
Networks [49.191062785007006]
Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs.
Existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths, or require a heavy fine-tuning process to recover the performance.
We propose a novel distribution-aware quantization scheme (DAQ) which facilitates accurate training-free quantization in ultra-low precision.
arXiv Detail & Related papers (2020-12-21T10:19:42Z) - Searching for Low-Bit Weights in Quantized Neural Networks [129.8319019563356]
Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators.
We present to regard the discrete weights in an arbitrary quantized neural network as searchable variables, and utilize a differential method to search them accurately.
arXiv Detail & Related papers (2020-09-18T09:13:26Z) - SQWA: Stochastic Quantized Weight Averaging for Improving the
Generalization Capability of Low-Precision Deep Neural Networks [29.187848543158992]
We present a new quantized neural network optimization approach, quantized weight averaging (SQWA)
The proposed approach includes floating-point model training, direct quantization of weights, capturing multiple low-precision models, averaging the captured models, and fine-tuning it with low-learning rates.
With SQWA training, we achieved state-of-the-art results for 2-bit QDNNs on CIFAR-100 and ImageNet datasets.
arXiv Detail & Related papers (2020-02-02T07:02:51Z)
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.