Lossy Research Articles

A Universal Random Coding Ensemble for Sample-Wise Lossy Compression.

We propose a universal ensemble for the random selection of rate-distortion codes which is asymptotically optimal in a sample-wise sense. According to this ensemble, each reproduction vector, x^, is selected independently at random under the probability distribution that is proportional to 2-LZ(x^), where LZ(x^) is the code length of x^ pertaining to the 1978 version of the Lempel-Ziv (LZ) algorithm. We show that, with high probability, the resulting codebook gives rise to an asymptotically optimal variable-rate lossy compression scheme under an arbitrary distortion measure, in the sense that a matching converse theorem also holds. According to the converse theorem, even if the decoder knew the ℓ-th order type of source vector in advance (ℓ being a large but fixed positive integer), the performance of the above-mentioned code could not have been improved essentially for the vast majority of codewords pertaining to source vectors in the same type. Finally, we present a discussion of our results, which includes among other things, a clear indication that our coding scheme outperforms the one that selects the reproduction vector with the shortest LZ code length among all vectors that are within the allowed distortion from the source vector.

Data Compression Versus Signal Fidelity Tradeoff in Wired-OR Analog-to-Digital Compressive Arrays for Neural Recording.

Future high-density and high channel count neural interfaces that enable simultaneous recording of tens of thousands of neurons will provide a gateway to study, restore and augment neural functions. However, building such technology within the bit-rate limit and power budget of a fully implantable device is challenging. The wired-OR compressive readout architecture addresses the data deluge challenge of a high channel count neural interface using lossy compression at the analog-to-digital interface. In this article, we assess the suitability of wired-OR for several steps that are important for neuroengineering, including spike detection, spike assignment and waveform estimation. For various wiring configurations of wired-OR and assumptions about the quality of the underlying signal, we characterize the trade-off between compression ratio and task-specific signal fidelity metrics. Using data from 18 large-scale microelectrode array recordings in macaque retina ex vivo, we find that for an event SNR of 7-10, wired-OR correctly detects and assigns at least 80% of the spikes with at least 50× compression. The wired-OR approach also robustly encodes action potential waveform information, enabling downstream processing such as cell-type classification. Finally, we show that by applying an LZ77-based lossless compressor (gzip) to the output of the wired-OR architecture, 1000× compression can be achieved over the baseline recordings.

Unified Architecture Adaptation for Compressed Domain Semantic Inference.

Advances in both lossy image compression and semantic content understanding have been greatly fueled by deep learning techniques, yet these two tasks have been developed separately for the past decades. In this work, we address the problem of directly executing semantic inference from quantized latent features in the deep compressed domain without pixel reconstruction. Although different methods have been proposed for this problem setting, they either are restrictive to a specific architecture, or are sub-optimal in terms of compressed domain task accuracy. In contrast, we propose a lightweight, plug-and-play solution which is generally compliant with popular learned image coders and deep vision models, making it attractive to vast applications. Our method adapts prevalent pixel domain neural models that are deployed for various vision tasks to directly accept quantized latent features (other than pixels). We further suggest training the compressed domain model by transferring knowledge from its corresponding pixel domain counterpart. Experiments show that our method is compliant with popular learned image coders and vision task models. Under fair comparison, our approach outperforms a baseline method by a) more than 3% top-1 accuracy for compressed domain classification, and b) more than 7% mIoU for compressed domain semantic segmentation, at various data rates.

Subject Review: Various Techniques for Image Compression

Due to the quick development of multimedia technology, now can see the increasing amount of multimedia data that is being generated or transmitted over the internet. digital image is one form of multimedia data, that can take different formats and different sizes. And here comes the main objective of image compression in transmitting or storing the data in an effective manner by decreasing the redundant or irrelevant information without significant loss of visual quality in image data. Compression of the images is utilized in various services, including TV broadcasts, satellite imagery, martial communications, webinars, medical imaging, weather reporting, etc. This paper provides a survey of the main techniques in image compression, covering both lossy & lossless approaches. The techniques that depend on lossy compression lose some of the image details during compression, while lossless compression techniques keep the image information without losing. Vector and scalar Quantization, transform coding, block truncation Coding, etc. are all examples of lossy approaches. Run length coding, entropy encoding, statistical coding, etc. are all examples of lossless techniques. This paper will assist the researchers in learning about these techniques and choosing appropriate techniques for their work.

A Rate-Distortion-Classification approach for lossy image compression

In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. The increasing demand for visual analysis applications, particularly in classification tasks, has emphasized the significance of considering semantic distortion in compressed images. To bridge the gap between image compression and visual analysis, we propose a Rate-Distortion-Classification (RDC) model for lossy image compression, offering a unified framework to optimize the trade-off between rate, distortion, and classification accuracy. The RDC model is extensively analyzed both statistically on a multi-distribution source and experimentally on the widely used MNIST dataset. The findings reveal that the RDC model exhibits desirable properties, including monotonic non-increasing and convex functions, under certain conditions. This work provides insights into the development of human-machine friendly compression methods and Video Coding for Machine (VCM) approaches, paving the way for end-to-end image compression techniques in real-world applications.

Residual encoding framework to compress DNN parameters for fast transfer

Efficient communication is significant for federated learning and DNN model deployment. However, transferring hundreds of millions of DNN parameters over networks with limited bandwidth results in long communication delays or even data losses. To alleviate or even remove the communication bottleneck, efficient methods for parameter compression can be applied. Inspired by video encoding, which exploits inter-frame similarity for compression, we investigate the strong temporal correlations of parameter updates in two near epochs of the DNN model and introduce a model parameter residual encoding framework. By transmitting encoded residual between model parameters in two near epochs, the receiver can reconstruct new model parameters and finish the updates with less communication cost. Furthermore, with respect to our framework, we develop lossless and lossy model parameter compression methods and demonstrate them on popular classification and detection networks. The results show that the lossless method can compress the data size of the parameters to less than 90%, and the lossy method can shrink the parameter size to less than 50% with a fair low loss. Our source code is released at https://github.com/zhouliguo/DNN_param_encode.

Multi-institutional PET/CT image segmentation using federated deep transformer learning

Background and ObjectiveGeneralizable and trustworthy deep learning models for PET/CT image segmentation necessitates large diverse multi-institutional datasets. However, legal, ethical, and patient privacy issues challenge sharing of datasets between different centers. To overcome these challenges, we developed a federated learning (FL) framework for multi-institutional PET/CT image segmentation. MethodsA dataset consisting of 328 FL (HN) cancer patients who underwent clinical PET/CT examinations gathered from six different centers was enrolled. A pure transformer network was implemented as fully core segmentation algorithms using dual channel PET/CT images. We evaluated different frameworks (single center-based, centralized baseline, as well as seven different FL algorithms) using 68 PET/CT images (20% of each center data). In particular, the implemented FL algorithms include clipping with the quantile estimator (ClQu), zeroing with the quantile estimator (ZeQu), federated averaging (FedAvg), lossy compression (LoCo), robust aggregation (RoAg), secure aggregation (SeAg), and Gaussian differentially private FedAvg with adaptive quantile clipping (GDP-AQuCl). ResultsThe Dice coefficient was 0.80±0.11 for both centralized and SeAg FL algorithms. All FL approaches achieved centralized learning model performance with no statistically significant differences. Among the FL algorithms, SeAg and GDP-AQuCl performed better than the other techniques. However, there was no statistically significant difference. All algorithms, except the center-based approach, resulted in relative errors less than 5% for SUVmax and SUVmean for all FL and centralized methods. Centralized and FL algorithms significantly outperformed the single center-based baseline. ConclusionsThe developed FL-based (with centralized method performance) algorithms exhibited promising performance for HN tumor segmentation from PET/CT images.

D-Semifaithful Codes That are Universal Over Both Memoryless Sources and Distortion Measures

We prove the existence of codebooks for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</i> -semifaithful lossy compression that are simultaneously universal with respect to both the class of finite-alphabet memoryless sources and the class of all bounded additive rational distortion measures. By applying independent random selection of the codewords according to a mixture of all memoryless sources, we achieve redundancy rates that are within <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> (log <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n/n</i> ) close to the empirical rate-distortion function of every given source vector with respect to every bounded, rational distortion measure.

Strange Images in Remote Sensing and Their Properties

Lossy image compression is used in many applications including remote sensing. Image size and number increase and this often leads to the necessity to apply image compression. In lossy compression, it is assumed that rate-distortion curves are monotonous functions and this assumption is put into basis of compression control. However, it has been shown recently that there are grayscale and color images called “strange” for which the rate-distortion curves are not monotonous. In this paper, we demonstrate that some remote sensing images can be strange as well and this takes place for JPEG and some other compression techniques. Analysis of properties for strange images using Spearman rank order correlation coefficient is carried out and it is shown that there several parameters characterizing image complexity that have a rather high correlation with probability that a given image is strange. For example, image entropy is one of such parameters.

Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

High-resolution (HR) images are usually downscaled to low-resolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified task and learns a bijective mapping between HR and LR via invertible networks. However, in real-world applications (e.g., social media), most images are compressed for transmission. Lossy compression will lead to irreversible information loss on LR images, hence damaging the inverse upscaling procedure and degrading the reconstruction accuracy. In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling. To tackle the distribution shift, we first develop an end-to-end asymmetric framework with two separate bijective mappings for high-quality and compressed LR images, respectively. Then, based on empirical analysis of this framework, we model the distribution of the lost information (including downscaling and compression) using isotropic Gaussian mixtures and propose the Enhanced Invertible Block to derive high-quality/compressed LR images in one forward pass. Besides, we design a set of losses to regularize the learned LR images and enhance the invertibility. Extensive experiments demonstrate the consistent improvements of SAIN across various image rescaling datasets in terms of both quantitative and qualitative evaluation under standard image compression formats (i.e., JPEG and WebP). Code is available at https://github.com/yang-jin-hai/SAIN.

Generalizing Downsampling from Regular Data to Graphs

Downsampling produces coarsened, multi-resolution representations of data and it is used, for example, to produce lossy compression and visualization of large images, reduce computational costs, and boost deep neural representation learning. Unfortunately, due to their lack of a regular structure, there is still no consensus on how downsampling should apply to graphs and linked data. Indeed reductions in graph data are still needed for the goals described above, but reduction mechanisms do not have the same focus on preserving topological structures and properties, while allowing for resolution-tuning, as is the case in regular data downsampling. In this paper, we take a step in this direction, introducing a unifying interpretation of downsampling in regular and graph data. In particular, we define a graph coarsening mechanism which is a graph-structured counterpart of controllable equispaced coarsening mechanisms in regular data. We prove theoretical guarantees for distortion bounds on path lengths, as well as the ability to preserve key topological properties in the coarsened graphs. We leverage these concepts to define a graph pooling mechanism that we empirically assess in graph classification tasks, providing a greedy algorithm that allows efficient parallel implementation on GPUs, and showing that it compares favorably against pooling methods in literature.

Conditional Encoder-Based Adaptive Deep Image Compression with Classification-Driven Semantic Awareness

This paper proposes a new algorithm for adaptive deep image compression (DIC) that can compress images for different purposes or contexts at different rates. The algorithm can compress images with semantic awareness, which means classification-related semantic features are better protected in lossy image compression. It builds on the existing conditional encoder-based DIC method and adds two features: a model-based rate-distortion-classification-perception (RDCP) framework to control the trade-off between rate and performance for different contexts, and a mechanism to generate coding conditions based on image complexity and semantic importance. The algorithm outperforms the QMAP2021 benchmark on the ImageNet dataset. Over the tested rate range, it improves the classification accuracy by 11% and the perceptual quality by 12.4%, 32%, and 1.3% on average for NIQE, LPIPS, and FSIM metrics, respectively.

Stream Aggregation with Compressed Sliding Windows

High performance stream aggregation is critical for many emerging applications that analyze massive volumes of data. Incoming data needs to be stored in a sliding window during processing, in case the aggregation functions cannot be computed incrementally. Updating the window with new incoming values and reading it to feed the aggregation functions are the two primary steps in stream aggregation. Although window updates can be supported efficiently using multi-level queues, frequent window aggregations remain a performance bottleneck as they put tremendous pressure on the memory bandwidth and capacity. This article addresses this problem by enhancing StreamZip, a dataflow stream aggregation engine that is able to compress the sliding windows. StreamZip deals with a number of data and control dependency challenges to integrate a compressor in the stream aggregation pipeline and alleviate the memory pressure posed by frequent aggregations. In addition, StreamZip incorporates a caching mechanism for dealing with skewed-key distributions in the incoming data stream. In doing so, StreamZip offers higher throughput as well as larger effective window capacity to support larger problems. StreamZip supports diverse compression algorithms offering both lossless and lossy compression to integers as well as floating-point numbers. Compared to designs without compression, StreamZip lossless and lossy designs achieve up to 7.5× and 22× higher throughput, while improving the effective memory capacity by up to 5× and 23×, respectively.

ECG compression technique using fast fractals in the Internet of medical things

AbstractECG signal is widely used in most cardiology e‐health systems. Patients may be monitored continuously for at least 12 h a day. Therefore, the ECG signal size transmitted to a hospital server during continuous monitoring is significant. Furthermore, transmission of the large size ECG signal is a power consuming process. ECG compression is one of the proposed solutions to overcome this problem. In this paper, a new fractal‐based ECG lossy compression technique is proposed. It is clear that fractal can use ECG signal self similarity characteristics efficiently to achieve high compression ratios. The proposed technique is based on developing the fractal model in conjunction with Iterated Function System. Fractal is well known as a time consuming technique, and therefore, new mathematical development is proposed to potentially reduce fractal computations. Experiments have proven the significant performance of fast fractal in comparison with the traditional version. Furthermore, the resultant compression ratios are close to the traditional fractal results and higher than other existing techniques.

Algorithm 1036: ATC, An Advanced Tucker Compression Library for Multidimensional Data

We present ATC, a C++ library for advanced Tucker-based lossy compression of dense multidimensional numerical data in a shared-memory parallel setting, based on the sequentially truncated higher-order singular value decomposition (ST-HOSVD) and bit plane truncation. Several techniques are proposed to improve speed, memory usage, error control and compression rate. First, a hybrid truncation scheme is described which combines Tucker rank truncation and TTHRESH quantization. We derive a novel expression to approximate the error of truncated Tucker decompositions in the case of core and factor perturbations. We parallelize the quantization and encoding scheme and adjust this phase to improve error control. Implementation aspects are described, such as an ST-HOSVD procedure using only a single transposition. We also discuss several usability features of ATC, including the presence of multiple interfaces, extensive data type support, and integrated downsampling of the decompressed data. Numerical results show that ATC maintains state-of-the-art Tucker compression rates while providing average speed-up factors of 2.2 to 3.5 and halving memory usage. Our compressor provides precise error control, deviating only 1.4% from the requested error on average. Finally, ATC often achieves higher compression than non-Tucker-based compressors in the high-error domain.

Black-box statistical prediction of lossy compression ratios for scientific data

Lossy compressors are increasingly adopted in scientific research, tackling volumes of data from experiments or parallel numerical simulations and facilitating data storage and movement. In contrast with the notion of entropy in lossless compression, no theoretical or data-based quantification of lossy compressibility exists for scientific data. Users rely on trial and error to assess lossy compression performance. As a strong data-driven effort toward quantifying lossy compressibility of scientific datasets, we provide a statistical framework to predict compression ratios of lossy compressors. Our method is a two-step framework where (i) compressor-agnostic predictors are computed and (ii) statistical prediction models relying on these predictors are trained on observed compression ratios. Proposed predictors exploit spatial correlations and notions of entropy and lossyness via the quantized entropy. We study 8+ compressors on 6 scientific datasets and achieve a median percentage prediction error less than 12%, which is substantially smaller than that of other methods while achieving at least a 8.8× speedup for searching for a specific compression ratio and 7.8× speedup for determining the best compressor out of a collection.

Neural Network Assisted Depth Map Packing for Compression Using Standard Hardware Video Codecs

Depth maps are needed by various graphics rendering and processing operations. Depth map streaming is often necessary when such operations are performed in a distributed system and it requires in most cases fast performing compression, which is why video codecs are often used. Hardware implementations of standard video codecs enable relatively high resolution and frame rate combinations, even on resource constrained devices, but unfortunately those implementations do not currently support RGB+depth extensions. However, they can be used for depth compression by first packing the depth maps into RGB or YUV frames. We investigate depth map compression using a combination of depth map packing followed by encoding with a standard video codec. We show that the precision at which depth maps are packed has a large and nontrivial impact on the resulting error caused by the combination of the packing scheme and lossy compression when the bitrate is constrained. Consequently, we propose a variable precision packing scheme assisted by a neural network model that predicts the optimal precision for each depth map given a bitrate constraint. We demonstrate that the model yields near optimal predictions and that it can be integrated into a game engine with very low overhead using modern hardware.

Textured Mesh Quality Assessment: Large-scale Dataset and Deep Learning-based Quality Metric

Over the past decade, three-dimensional (3D) graphics have become highly detailed to mimic the real world, exploding their size and complexity. Certain applications and device constraints necessitate their simplification and/or lossy compression, which can degrade their visual quality. Thus, to ensure the best Quality of Experience, it is important to evaluate the visual quality to accurately drive the compression and find the right compromise between visual quality and data size. In this work, we focus on subjective and objective quality assessment of textured 3D meshes. We first establish a large-scale dataset, which includes 55 source models quantitatively characterized in terms of geometric, color, and semantic complexity, and corrupted by combinations of five types of compression-based distortions applied on the geometry, texture mapping, and texture image of the meshes. This dataset contains over 343k distorted stimuli. We propose an approach to select a challenging subset of 3,000 stimuli for which we collected 148,929 quality judgments from over 4,500 participants in a large-scale crowdsourced subjective experiment. Leveraging our subject-rated dataset, a learning-based quality metric for 3D graphics was proposed. Our metric demonstrates state-of-the-art results on our dataset of textured meshes and on a dataset of distorted meshes with vertex colors. Finally, we present an application of our metric and dataset to explore the influence of distortion interactions and content characteristics on the perceived quality of compressed textured meshes.

Accelerated dynamic data reduction using spatial and temporal properties

Due to improvements in high-performance computing (HPC) capabilities, many of today’s applications produce petabytes worth of data, causing bottlenecks within the system. Importance-based sampling methods, including our spatio-temporal hybrid data sampling method, are capable of resolving these bottlenecks. While our hybrid method has been shown to outperform existing methods, its effectiveness relies heavily on user parameters, such as histogram bins, error threshold, or number of regions. Moreover, the throughput it demonstrates must be higher to avoid becoming a bottleneck itself. In this article, we resolve both of these issues. First, we assess the effects of several user input parameters and detail techniques to help determine optimal parameters. Next, we detail and implement accelerated versions of our method using OpenMP and CUDA. Upon analyzing our implementations, we find 9.8× to 31.5× throughput improvements. Next, we demonstrate how our method can accept different base sampling algorithms and the effects these different algorithms have. Finally, we compare our sampling methods to the lossy compressor cuSZ in terms of data preservation and data movement.

High-resolution image compression algorithms in remote sensing imaging

Digital image processing (DIP) has great application values in many fields, especially in remote sensing image processing, which represents the acquisition, enhancement, analysis, encoding, transmission, and storage of remote sensing images. With the development of chip technology and parallel computing technology, various digital image processing technologies have been successfully applied to satellite applications to help researchers exploit reliable information from remote-sensing images. However, the huge amount of images generated by ultra-high resolution optical remote sensing satellites put great pressure on existing transmission, storage, and processing technologies. Therefore, this paper proposes a spatio-temporal compression pipeline for remote sensing images based on lossy compression methods with ultra-high compression ratios to reduce the overhead required for the transmission and storage of remote sensing images while maintaining the quality of the compressed images. The experimental results show that the proposed method outperforms the classical image compression such as JPEG-2000.