Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks

Johnston, Nick; Vincent, Damien; Minnen, David; Covell, Michele; Singh, Rajesh; Chinen, Troy; Hwang, Sung Jin; Shor, Joel; Toderici, George

doi:10.48550/arxiv.1703.10114

Cited by 19 publications

(44 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, by utilizing machine learning methods, one can implement task-based quantizers without the need to explicitly know the underlying model and to analytically derive the proper quantization rule. Existing works on deep learning for quantization typically focus on image compression [20]- [24], where the goal is to represent the analog image using a single quantization rule, i.e., non task-based quantization.…”

Section: Introductionmentioning

confidence: 99%

Hardware-Limited Task-Based Quantization

Shlezinger

Eldar

Rodrigues

2019

IEEE Trans. Signal Process.

108

View full text Add to dashboard Cite

Quantizers play a critical role in digital signal processing systems. Recent works have shown that the performance of quantization systems acquiring multiple analog signals using scalar analog-to-digital converters (ADCs) can be significantly improved by properly processing the analog signals prior to quantization. However, the design of such hybrid quantizers is quite complex, and their implementation requires complete knowledge of the statistical model of the analog signal, which may not be available in practice. In this work we design data-driven task-oriented quantization systems with scalar ADCs, which determine how to map an analog signal into its digital representation using deep learning tools.These representations are designed to facilitate the task of recovering underlying information from the quantized signals, which can be a set of parameters to estimate, or alternatively, a classification task. By utilizing deep learning, we circumvent the need to explicitly recover the system model and to find the proper quantization rule for it. Our main target application is multiple-input multiple-output (MIMO) communication receivers, which simultaneously acquire a set of analog signals, and are commonly subject to constraints on the number of bits. Our results indicate that, in a MIMO channel estimation setup, the proposed deep task-bask quantizer is capable of approaching the optimal performance limits dictated by indirect rate-distortion theory, achievable using vector quantizers and requiring complete knowledge of the underlying statistical model. Furthermore, for a symbol detection scenario, it is demonstrated that the proposed approach can realize reliable bit-efficient hybrid MIMO receivers capable of setting their quantization rule in light of the task, e.g., to minimize the bit error rate.

show abstract

Section: Introductionmentioning

confidence: 99%

Hardware-Limited Task-Based Quantization

Shlezinger

Eldar

Rodrigues

2019

IEEE Trans. Signal Process.

108

View full text Add to dashboard Cite

show abstract

“…The CABAC model updates the model parameters during the process of encoding/decoding according to the content of the image. With the fast development of deep learning techniques, deep neural networks have been used to achieve more accurate statistical estimations [9,10,11,12,13,14,15]. Unlike traditional image/video coding systems [5,7], which encode residuals between the input symbols and the predicted symbols, deep neural network-based image/video compression systems normally use the estimated value distribution function directly, since deep neural networks are more capable of modeling complicated distribution functions.…”

Section: Introductionmentioning

confidence: 99%

Lossless Image Compression Using a Multi-scale Progressive Statistical Model

Zhang

Cricri

Tavakoli

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Lossless image compression is an important technique for image storage and transmission when information loss is not allowed. With the fast development of deep learning techniques, deep neural networks have been used in this field to achieve a higher compression rate. Methods based on pixel-wise autoregressive statistical models have shown good performance. However, the sequential processing way prevents these methods to be used in practice. Recently, multi-scale autoregressive models have been proposed to address this limitation. Multi-scale approaches can use parallel computing systems efficiently and build practical systems. Nevertheless, these approaches sacrifice compression performance in exchange for speed. In this paper, we propose a multi-scale progressive statistical model that takes advantage of the pixel-wise approach and the multi-scale approach. We developed a flexible mechanism where the processing order of the pixels can be adjusted easily. Our proposed method outperforms the state-of-the-art lossless image compression methods on two large benchmark datasets by a significant margin without degrading the inference speed dramatically.

show abstract

“…Deep learning-based image compression [1,2,3,4,5,6,7,8,9,10,11] has shown the potential to outperform standard codecs such as JPEG2000, the H.265/HEVC-based BPG image codec [12], and the new versatile video coding test model (VTM) [13]. Learned image compression was first used in [10] to compress thumbnail images using long short-term memory (LSTM)-based recurrent neural networks (RNNs) in which better SSIM results than JPEG and WebP were reported.…”

Section: Introductionmentioning

confidence: 99%

“…Learned image compression was first used in [10] to compress thumbnail images using long short-term memory (LSTM)-based recurrent neural networks (RNNs) in which better SSIM results than JPEG and WebP were reported. This approach was generalized in [5], which utilized spatially adaptive bit allocation to further improve the performance.…”

Section: Introductionmentioning

confidence: 99%

Generalized Octave Convolutions for Learned Multi-Frequency Image Compression

Akbari,

Liang,

Han

et al. 2020

Preprint

View full text Add to dashboard Cite

Learned image compression has recently shown the potential to outperform all standard codecs. The state-of-the-art ratedistortion performance has been achieved by context-adaptive entropy approaches in which hyperprior and autoregressive models are jointly utilized to effectively capture the spatial dependencies in the latent representations. However, the latents contain a mixture of high and low frequency information, which has inefficiently been represented by features maps of the same spatial resolution in previous works. In this paper, we propose the first learned multi-frequency image compression approach that uses the recently developed octave convolutions to factorize the latents into high and low frequencies. Since the low frequency is represented by a lower resolution, their spatial redundancy is reduced, which improves the compression rate. Moreover, octave convolutions impose effective high and low frequency communication, which can improve the reconstruction quality. We also develop novel generalized octave convolution and octave transposed-convolution architectures with internal activation layers to preserve the spatial structure of the information. Our experiments show that the proposed scheme outperforms all standard codecs and learning-based methods in both PSNR and MS-SSIM metrics, and establishes the new state of the art for learned image compression.

show abstract

Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks

Cited by 19 publications

References 0 publications

Hardware-Limited Task-Based Quantization

Hardware-Limited Task-Based Quantization

Lossless Image Compression Using a Multi-scale Progressive Statistical Model

Generalized Octave Convolutions for Learned Multi-Frequency Image Compression

Contact Info

Product

Resources

About