Color and structure are the two pillars that combine to give an image its meaning. Interested in critical structures for neural network recognition, we isolate the influence of colors by limiting the color space to just a few bits, and find structures that enable network recognition under such constraints. To this end, we propose a color quantization network, ColorCNN, which learns to structure an image in limited color spaces by minimizing the classification loss. Building upon the architecture and insights of ColorCNN, we introduce ColorCNN+, which supports multiple color space size configurations, and addresses the previous issues of poor recognition accuracy and undesirable visual fidelity under large color spaces. Via a novel imitation learning approach, ColorCNN+ learns to cluster colors like traditional color quantization methods. This reduces overfitting and helps both visual fidelity and recognition accuracy under large color spaces. Experiments verify that ColorCNN+ achieves very competitive results under most circumstances, preserving both key structures for network recognition and visual fidelity with accurate colors. We further discuss differences between key structures and accurate colors, and their specific contributions to network recognition. For potential applications, we show that ColorCNNs can be used as image compression methods for network recognition.
Image compression is an essential and last processing unit in the camera image signal processing (ISP) pipeline. While many studies have been made to replace the conventional ISP pipeline with a single end-to-end optimized deep learning model, image compression is barely considered as a part of the model. In this paper, we investigate the designing of a fully end-to-end optimized camera ISP incorporating image compression. To this end, we propose RAWtoBit network (RBN) that can effectively perform both tasks simultaneously. RBN is further improved with a novel knowledge distillation scheme by introducing two teacher networks specialized in each task. Extensive experiments demonstrate that our proposed method significantly outperforms alternative approaches in terms of rate-distortion trade-off.
Yes - This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject. We adopt a recently proposed racial phenotype-based bias analysis methodology to measure the effect of varying levels of lossy compression across racial phenotype categories. Additionally, we determine the relationship between chroma-subsampling and race-related phenotypes for recognition performance. Prior work investigates the impact of lossy JPEG compression algorithm on contemporary face recognition performance. However, there is a gap in how this impact varies with different race-related inter-sectional groups and the cause of this impact. Via an extensive experimental setup, we demonstrate that common lossy image compression approaches have a more pronounced negative impact on facial recognition performance for specific racial phenotype categories such as darker skin tones (by up to 34.55\%). Furthermore, removing chroma-subsampling during compression improves the false matching rate (up to 15.95\%) across all phenotype categories affected by the compression, including darker skin tones, wide noses, big lips, and monolid eye categories. In addition, we outline the characteristics that may be attributable as the underlying cause of such phenomenon for lossy compression algorithms such as JPEG.
JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings. However, applying such lossy compression on images processed by deep neural networks can lead to significant accuracy degradation. Inspired by the curriculum learning paradigm, we propose a training approach called curriculum pre-training (CPT) for crowd counting on compressed images, which alleviates the drop in accuracy resulting from lossy compression. We verify the effectiveness of our approach by extensive experiments on three crowd counting datasets, two crowd counting DNN models and various levels of compression. The proposed training method is not overly sensitive to hyper-parameters, and reduces the error, particularly for heavily compressed images, by up to 19.70%.
With the development of streaming media technology, increasing communication relies on sound and visual information, which puts a massive burden on online media. Data compression becomes increasingly important to reduce the volume of data transmission and storage. To further improve the efficiency of image compression, researchers utilize various image processing methods to compensate for the limitations of conventional codecs and advanced learning-based compression methods. Instead of modifying the image compression oriented approaches, we propose a unified image compression preprocessing framework, called Kuchen, which aims to further improve the performance of existing codecs. The framework consists of a hybrid data labeling system along with a learning-based backbone to simulate personalized preprocessing. As far as we know, this is the first exploration of setting a unified preprocessing benchmark in image compression tasks. Results demonstrate that the modern codecs optimized by our unified preprocessing framework constantly improve the efficiency of the state-of-the-art compression.
Recently, learning-based image compression methods that utilize convolutional neural layers have been developed rapidly. Rescaling modules such as batch normalization which are often used in convolutional neural networks do not operate adaptively for the various inputs. Therefore, Generalized Divisible Normalization(GDN) has been widely used in image compression to rescale the input features adaptively across both spatial and channel axes. However, the representation power or degree of freedom of GDN is severely limited. Additionally, GDN cannot consider the spatial correlation of an image. To handle the limitations of GDN, we construct an expanded form of the adaptive scaling module, named Expanded Adaptive Scaling Normalization(EASN). First, we exploit the swish function to increase the representation ability. Then, we increase the receptive field to make the adaptive rescaling module consider the spatial correlation. Furthermore, we introduce an input mapping function to give the module a higher degree of freedom. We demonstrate how our EASN works in an image compression network using the visualization results of the feature map, and we conduct extensive experiments to show that our EASN increases the rate-distortion performance remarkably, and even outperforms the VVC intra at a high bit rate.
Learned image compression allows achieving state-of-the-art accuracy and compression ratios, but their relatively slow runtime performance limits their usage. While previous attempts on optimizing learned image codecs focused more on the neural model and entropy coding, we present an alternative method to improving the runtime performance of various learned image compression models. We introduce multi-threaded pipelining and an optimized memory model to enable GPU and CPU workloads asynchronous execution, fully taking advantage of computational resources. Our architecture alone already produces excellent performance without any change to the neural model itself. We also demonstrate that combining our architecture with previous tweaks to the neural models can further improve runtime performance. We show that our implementations excel in throughput and latency compared to the baseline and demonstrate the performance of our implementations by creating a real-time video streaming encoder-decoder sample application, with the encoder running on an embedded device.
Learned image compression has achieved extraordinary rate-distortion performance in PSNR and MS-SSIM compared to traditional methods. However, it suffers from intensive computation, which is intolerable for real-world applications and leads to its limited industrial application for now. In this paper, we introduce neural architecture search (NAS) to designing more efficient networks with lower latency, and leverage quantization to accelerate the inference process. Meanwhile, efforts in engineering like multi-threading and SIMD have been made to improve efficiency. Optimized using a hybrid loss of PSNR and MS-SSIM for better visual quality, we obtain much higher MS-SSIM than JPEG, JPEG XL and AVIF over all bit rates, and PSNR between that of JPEG XL and AVIF. Our software implementation of LIC achieves comparable or even faster inference speed compared to jpeg-turbo while being multiple times faster than JPEG XL and AVIF. Besides, our implementation of LIC reaches stunning throughput of 145 fps for encoding and 208 fps for decoding on a Tesla T4 GPU for 1080p images. On CPU, the latency of our implementation is comparable with JPEG XL.
Object detectors are vital to many modern computer vision applications. However, even state-of-the-art object detectors are not perfect. On two images that look similar to human eyes, the same detector can make different predictions because of small image distortions like camera sensor noise and lighting changes. This problem is called inconsistency. Existing accuracy metrics do not properly account for inconsistency, and similar work in this area only targets improvements on artificial image distortions. Therefore, we propose a method to use non-artificial video frames to measure object detection consistency over time, across frames. Using this method, we show that the consistency of modern object detectors ranges from 83.2% to 97.1% on different video datasets from the Multiple Object Tracking Challenge. We conclude by showing that applying image distortion corrections like .WEBP Image Compression and Unsharp Masking can improve consistency by as much as 5.1%, with no loss in accuracy.
In recent years, with the development of deep neural networks, end-to-end optimized image compression has made significant progress and exceeded the classic methods in terms of rate-distortion performance. However, most learning-based image compression methods are unlabeled and do not consider image semantics or content when optimizing the model. In fact, human eyes have different sensitivities to different content, so the image content also needs to be considered. In this paper, we propose a content-oriented image compression method, which handles different kinds of image contents with different strategies. Extensive experiments show that the proposed method achieves competitive subjective results compared with state-of-the-art end-to-end learned image compression methods or classic methods.
Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data. Recent works for image compression indicate that compression of images based on SMoE models can provide competitive performance to the state-of-the-art. Unfortunately, the iterative model-building process at the encoder comes with excessive computational demands. In this paper we introduce a novel edge-aware Autoencoder (AE) strategy designed to avoid the time-consuming iterative optimization of SMoE models. This is done by directly mapping pixel blocks to model parameters for compression, in spirit similar to recent works on "unfolding" of algorithms, while maintaining full compatibility to the established SMoE framework. With our plug-in AE encoder, we achieve a quantum-leap in performance with encoder run-time savings by a factor of 500 to 1000 with even improved image reconstruction quality. For image compression the plug-in AE encoder has real-time properties and improves RD-performance compared to our previous works.
In this paper, two 8-point multiplication-free DCT approximations based on the Chen's factorization are proposed and their fast algorithms are also derived. Both transformations are assessed in terms of computational cost, error energy, and coding gain. Experiments with a JPEG-like image compression scheme are performed and results are compared with competing methods. The proposed low-complexity transforms are scaled according to Jridi-Alfalou-Meher algorithm to effect 16- and 32-point approximations. The new sets of transformations are embedded into an HEVC reference software to provide a fully HEVC-compliant video coding scheme. We show that approximate transforms can outperform traditional transforms and state-of-the-art methods at a very low complexity cost.
In the era of multinational cooperation, gathering and analyzing the satellite images are getting easier and more important. Typical procedure of the satellite image analysis include transmission of the bulky image data from satellite to the ground producing significant overhead. To reduce the amount of the transmission overhead while making no harm to the analysis result, we propose a novel image compression scheme RDIC in this paper. RDIC is a reasoning based image compression scheme that compresses an image according to the pixel importance score acquired from the analysis model itself. From the experimental results we showed that our RDIC scheme successfully captures the important regions in an image showing high compression rate and low accuracy loss.
High levels of noise usually exist in today's captured images due to the relatively small sensors equipped in the smartphone cameras, where the noise brings extra challenges to lossy image compression algorithms. Without the capacity to tell the difference between image details and noise, general image compression methods allocate additional bits to explicitly store the undesired image noise during compression and restore the unpleasant noisy image during decompression. Based on the observations, we optimize the image compression algorithm to be noise-aware as joint denoising and compression to resolve the bits misallocation problem. The key is to transform the original noisy images to noise-free bits by eliminating the undesired noise during compression, where the bits are later decompressed as clean images. Specifically, we propose a novel two-branch, weight-sharing architecture with plug-in feature denoisers to allow a simple and effective realization of the goal with little computational cost. Experimental results show that our method gains a significant improvement over the existing baseline methods on both the synthetic and real-world datasets. Our source code is available at https://github.com/felixcheng97/DenoiseCompression.
Images and video frames captured by cameras placed throughout smart cities are often transmitted over the network to a server to be processed by deep neural networks for various tasks. Transmission of raw images, i.e., without any form of compression, requires high bandwidth and can lead to congestion issues and delays in transmission. The use of lossy image compression techniques can reduce the quality of the images, leading to accuracy degradation. In this paper, we analyze the effect of applying low-overhead lossy image compression methods on the accuracy of visual crowd counting, and measure the trade-off between bandwidth reduction and the obtained accuracy.
We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider a pair of stereo images, which have overlapping fields of view, and are captured by a synchronized and calibrated pair of cameras as correlated image sources. In previously proposed methods, the encoder transforms the input image to a latent representation using a deep neural network, and compresses the quantized latent representation losslessly using entropy coding. The decoder decodes the entropy-coded quantized latent representation, and reconstructs the input image using this representation and the available side information. In the proposed method, the decoder employs a cross-attention module to align the feature maps obtained from the received latent representation of the input image and a latent representation of the side information. We argue that aligning the correlated patches in the feature maps allows better utilization of the side information. We empirically demonstrate the competitiveness of the proposed algorithm on KITTI and Cityscape datasets of stereo image pairs. Our experimental results show that the proposed architecture is able to exploit the decoder-only side information in a more efficient manner compared to previous works.
We propose Deep Lossless Image Coding (DLIC), a full resolution learned lossless image compression algorithm. Our algorithm is based on a neural network combined with an entropy encoder. The neural network performs a density estimation on each pixel of the source image. The density estimation is then used to code the target pixel, beating FLIF in terms of compression rate. Similar approaches have been attempted. However, long run times make them unfeasible for real world applications. We introduce a parallelized GPU based implementation, allowing for encoding and decoding of grayscale, 8-bit images in less than one second. Because DLIC uses a neural network to estimate the probabilities used for the entropy coder, DLIC can be trained on domain specific image data. We demonstrate this capability by adapting and training DLIC with Magnet Resonance Imaging (MRI) images.
JPEG-XS offers low complexity image compression for applications with constrained but reasonable bit-rate, and low latency. Our paper explores the deployment of JPEG-XS on lossy packet networks. To preserve low latency, Forward Error Correction (FEC) is envisioned as the protection mechanism of interest. Despite the JPEG-XS codestream is not scalable in essence, we observe that the loss of a codestream fraction impacts the decoded image quality differently, depending on whether this codestream fraction corresponds to codestream headers, to coefficients significance information, or to low/high frequency data, respectively. Hence, we propose a rate-distortion optimal unequal error protection scheme that adapts the redundancy level of Reed-Solomon codes according to the rate of channel losses and the type of information protected by the code. Our experiments demonstrate that, at 5% loss rates, it reduces the Mean Squared Error by up to 92% and 65%, compared to a transmission without and with optimal but equal protection, respectively.
Privacy-preserving machine learning (PPML) solutions are gaining widespread popularity. Among these, many rely on homomorphic encryption (HE) that offers confidentiality of the model and the data, but at the cost of large latency and memory requirements. Pruning neural network (NN) parameters improves latency and memory in plaintext ML but has little impact if directly applied to HE-based PPML. We introduce a framework called HE-PEx that comprises new pruning methods, on top of a packing technique called tile tensors, for reducing the latency and memory of PPML inference. HE-PEx uses permutations to prune additional ciphertexts, and expansion to recover inference loss. We demonstrate the effectiveness of our methods for pruning fully-connected and convolutional layers in NNs on PPML tasks, namely, image compression, denoising, and classification, with autoencoders, multilayer perceptrons (MLPs) and convolutional neural networks (CNNs). We implement and deploy our networks atop a framework called HElayers, which shows a 10-35% improvement in inference speed and a 17-35% decrease in memory requirement over the unpruned network, corresponding to 33-65% fewer ciphertexts, within a 2.5% degradation in inference accuracy over the unpruned network. Compared to the state-of-the-art pruning technique for PPML, our techniques generate networks with 70% fewer ciphertexts, on average, for the same degradation limit.
This paper presents improvements and novel additions to our recent work on end-to-end optimized hierarchical bi-directional video compression to further advance the state-of-the-art in learned video compression. As an improvement, we combine motion estimation and prediction modules and compress refined residual motion vectors for improved rate-distortion performance. As novel addition, we adapted the gain unit proposed for image compression to flexible-rate video compression in two ways: first, the gain unit enables a single encoder model to operate at multiple rate-distortion operating points; second, we exploit the gain unit to control bit allocation among intra-coded vs. bi-directionally coded frames by fine tuning corresponding models for truly flexible-rate learned video coding. Experimental results demonstrate that we obtain state-of-the-art rate-distortion performance exceeding those of all prior art in learned video coding.