Lossy Image Compression with Compressive Autoencoders

Theis, Lucas; Shi, Wenzhe; Cunningham, Andrew A.; Huszár, Ferenc

doi:10.48550/arxiv.1703.00395

Cited by 109 publications

(198 citation statements)

References 16 publications

Supporting

Mentioning

196

Contrasting

Order By: Relevance

“…RNN based models [16,34,35] compress images or residual information from the previous step iteratively, while CNN based models typically transform images into compact latent representations for further entropy coding. Some early works [1,4,33] solve the problem of non-differential quantization and rate estimation. Afterward, some works [4,5,9,13,14,19,28] focus on designing powerful entropy models to improve the accuracy of rate estimation.…”

Section: Image Compressionmentioning

confidence: 99%

DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

Ma¹,

Zhai²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

Scalable coding, which can adapt to channel bandwidth variation, performs well in today's complex network environment. However, the existing scalable compression methods face two challenges: reduced compression performance and insufficient scalability. In this paper, we propose the first learned fine-grained scalable image compression model (DeepFGS) to overcome the above two shortcomings. Specifically, we introduce a feature separation backbone to divide the image information into basic and scalable features, then redistribute the features channel by channel through an information rearrangement strategy. In this way, we can generate a continuously scalable bitstream via onepass encoding. In addition, we reuse the decoder to reduce the parameters and computational complexity of DeepFGS. Experiments demonstrate that our DeepFGS outperforms all learning-based scalable image compression models and conventional scalable image codecs in PSNR and MS-SSIM metrics. To the best of our knowledge, our DeepFGS is the first exploration of learned fine-grained scalable coding, which achieves the finest scalability compared with learning-based methods.

show abstract

Section: Image Compressionmentioning

confidence: 99%

DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

Ma¹,

Zhai²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…We reconstructed the data from the first N z principal components to obtain the data compression. Autoencoder also provides data compression by constraining the number of codes (N z ) to a small number 24,25 . We used a fully connected neural-network encoder and decoder with three hidden layers of (D, 128, 64, 32, N z ) and (N z , 32, 64, 128, D) with rectified linear unit (ReLU) activation functions.…”

Section: Experiments With Simulated Annealingmentioning

confidence: 99%

Lossy compression of statistical data using quantum annealer

Yoon,

Nguyen,

Chang

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a new lossy compression algorithm for statistical floating-point data through a representation learning with binary variables. The algorithm finds a set of basis vectors and their binary coefficients that precisely reconstruct the original data. The optimization for the basis vectors is performed classically, while binary coefficients are retrieved through both simulated and quantum annealing for comparison. A bias correction procedure is also presented to estimate and eliminate the error and bias introduced from the inexact reconstruction of the lossy compression for statistical data analyses. The compression algorithm is demonstrated on two different datasets of lattice quantum chromodynamics simulations. The results obtained using simulated annealing show 3.5 times better compression performance than the algorithms based on a neural-network autoencoder and principal component analysis. Calculations using quantum annealing also show promising results, but performance is limited by the integrated control error of the quantum processing unit, which yields large uncertainties in the biases and coupling parameters. Hardware comparison is further studied between the previous generation D-Wave 2000Q and the current D-Wave Advantage system. Our study shows that the Advantage system is more likely to obtain low-energy solutions for the problems than the 2000Q.

show abstract

“…The focus of [4] is to optimize the mean squared error (MSE) and multiscale structural similarity for image quality assessment (MS-SSIM) between decompressed images and the originals. In [6], the images are compressed through an encoder, and a traditional quantization method is applied to reduce the bitrate. GAN-based models are widely explored in image compression tasks.…”

Section: Image Compressionmentioning

confidence: 99%

Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization

Liu¹,

Lee²,

Cao³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals. The compressed signal is represented as a latent vector and fed into a generator network that is trained to produce high quality realistic signals that minimize a target objective function. To efficiently quantize the compressed signal, non-uniformly quantized optimal latent vectors are identified by iterative back-propagation with alternating direction method of multipliers (ADMM) optimization performed for each iteration. The performance of the proposed signal compression method is assessed using multiple metrics including PSNR and MS-SSIM for image compression and also PESR, Kaldi, LSTM, and MLP performance for speech compression. Test results show that the proposed work outperforms recent state-of-the-art hand-crafted and deep learning-based signal compression methods.

show abstract

Lossy Image Compression with Compressive Autoencoders

Cited by 109 publications

References 16 publications

DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

Lossy compression of statistical data using quantum annealer

Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization

Contact Info

Product

Resources

About