paper-with-me

Papers

End-to-End Learned Image Compression with Quantized Weights and Activations

2021-11-17 · Heming Sun, Lu Yu, Jiro Katto

End-to-end Learned image compression (LIC) has reached the traditional hand-crafted methods such as BPG (HEVC intra) in terms of the coding gain. However, the large network size prohibits the usage of LIC on resource-limited embedded systems. This paper reduces the network complexity by quantizing both weights and activations. 1) For the weight quantization, we study different kinds of grouping and quantization scheme at first. A channel-wise non-linear quantization scheme is determined based on the coding gain analysis. After that, we propose a fine tuning scheme to clip the weights within a certain range so that the quantization error can be reduced. 2) For the activation quantization, we first propose multiple non-linear quantization codebooks with different maximum dynamic ranges. By selecting an optimal one through a multiplexer, the quantization range can be saturated to the greatest extent. In addition, we also exploit the mean-removed quantization for the analysis transform outputs in order to reduce the bit-width cost for the specific channel with the large non-zero mean. By quantizing each weight and activation element from 32-bit floating point to 8-bit fixed point, the memory cost for both weight and activation can be reduced by 75% with negligible coding performance loss. As a result, our quantized LIC can still outperform BPG in terms of MS-SSIM. To our best knowledge, this is the first work to give a complete analysis on the coding gain and the memory cost for a quantized LIC network, which validates the feasibility of the hardware implementation.

📄 PDF Abstract BibTeX arXiv:2111.09348

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionMS-SSIMQuantizationSSIM

Similar Papers 제목 키워드 기반

Quantized Decoder in Learned Image Compression for Deterministic Reconstruction

2023-12-18 · Esin Koyuncu, Timofey Solovyev, Johannes Sauer, Elena Alshina 외

Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices. This paper shows a method to achieve a deterministic reconstructed …

DecoderImage CompressionQuantization

Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks

2020-03-04 · Jun Chen, Yong liu, Hao Zhang, Shengnan Hou 외

The quantized neural networks (QNNs) can be useful for neural network acceleration and compression, but during the training process they pose a challenge: how to propagate the gradient of loss function through the graph …

Learning Sparse Low-Precision Neural Networks With Learnable Regularization

2018-09-01 · Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backwa…

Image Super-ResolutionL2 RegularizationQuantizationSuper-Resolution

Coded Deep Learning: Framework and Algorithm

2025-01-16 · En-hui Yang, Shayan Mohajer Hamidi

The success of deep learning (DL) is often achieved with large models and high complexity during both training and post-training inferences, hindering training in resource-limited settings. To alleviate these issues, thi…

Deep Learning

Low-Rank Correction for Quantized LLMs

2024-12-10 · Meyer Scetbon, James Hensman

We consider the problem of model compression for Large Language Models (LLMs) at post-training time, where the task is to compress a well-trained model using only a small set of calibration input data. In this work, we i…

Model CompressionQuantization