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.
Over recent years, deep learning-based computer vision systems have been applied to images at an ever-increasing pace, oftentimes representing the only type of consumption for those images. Given the dramatic explosion in the number of images generat
ed per day, a question arises: how much better would an image codec targeting machine-consumption perform against state-of-the-art codecs targeting human-consumption? In this paper, we propose an image codec for machines which is neural network (NN) based and end-to-end learned. In particular, we propose a set of training strategies that address the delicate problem of balancing competing loss functions, such as computer vision task losses, image distortion losses, and rate loss. Our experimental results show that our NN-based codec outperforms the state-of-the-art Versa-tile Video Coding (VVC) standard on the object detection and instance segmentation tasks, achieving -37.87% and -32.90% of BD-rate gain, respectively, while being fast thanks to its compact size. To the best of our knowledge, this is the first end-to-end learned machine-targeted image codec.
Today, according to the Cisco Annual Internet Report (2018-2023), the fastest-growing category of Internet traffic is machine-to-machine communication. In particular, machine-to-machine communication of images and videos represents a new challenge an
d opens up new perspectives in the context of data compression. One possible solution approach consists of adapting current human-targeted image and video coding standards to the use case of machine consumption. Another approach consists of developing completely new compression paradigms and architectures for machine-to-machine communications. In this paper, we focus on image compression and present an inference-time content-adaptive finetuning scheme that optimizes the latent representation of an end-to-end learned image codec, aimed at improving the compression efficiency for machine-consumption. The conducted experiments show that our online finetuning brings an average bitrate saving (BD-rate) of -3.66% with respect to our pretrained image codec. In particular, at low bitrate points, our proposed method results in a significant bitrate saving of -9.85%. Overall, our pretrained-and-then-finetuned system achieves -30.54% BD-rate over the state-of-the-art image/video codec Versatile Video Coding (VVC).
We present Mask-GVAE, a variational generative model for blind denoising large discrete graphs, in which blind denoising means we dont require any supervision from clean graphs. We focus on recovering graph structures via deleting irrelevant edges an
d adding missing edges, which has many applications in real-world scenarios, for example, enhancing the quality of connections in a co-authorship network. Mask-GVAE makes use of the robustness in low eigenvectors of graph Laplacian against random noise and decomposes the input graph into several stable clusters. It then harnesses the huge computations by decoding probabilistic smoothed subgraphs in a variational manner. On a wide variety of benchmarks, Mask-GVAE outperforms competing approaches by a significant margin on PSNR and WL similarity.
Data hiding is the procedure of encoding desired information into the cover image to resist potential noises while ensuring the embedded image has few perceptual perturbations from the original one. Recently, with the tremendous successes gained by d
eep neural networks in various fields, the researches of data hiding with deep learning models have attracted an increasing number of attentions. In the data hiding task, each pixel of cover images should be treated differently since they have divergent tolerabilities. The neglect of considering the sensitivity of each pixel will inevitably affect the model robustness for information hiding. Targeting this problem, we propose a novel deep data hiding scheme with Inverse Gradient Attention (IGA), combing the ideas of adversarial learning and attention mechanism to endow different sensitivities for different pixels. With the proposed component, the model can spotlight pixels with more robustness for data hiding. Empirically, extensive experiments show that the proposed model outperforms the state-of-the-art methods on two prevalent datasets under multiple evaluations. Besides, we further identify and discuss the connections between the proposed inverse gradient attention and high-frequency regions within images.
In this paper we present an end-to-end meta-learned system for image compression. Traditional machine learning based approaches to image compression train one or more neural network for generalization performance. However, at inference time, the enco
der or the latent tensor output by the encoder can be optimized for each test image. This optimization can be regarded as a form of adaptation or benevolent overfitting to the input content. In order to reduce the gap between training and inference conditions, we propose a new training paradigm for learned image compression, which is based on meta-learning. In a first phase, the neural networks are trained normally. In a second phase, the Model-Agnostic Meta-learning approach is adapted to the specific case of image compression, where the inner-loop performs latent tensor overfitting, and the outer loop updates both encoder and decoder neural networks based on the overfitting performance. Furthermore, after meta-learning, we propose to overfit and cluster the bias terms of the decoder on training image patches, so that at inference time the optimal content-specific bias terms can be selected at encoder-side. Finally, we propose a new probability model for lossless compression, which combines concepts from both multi-scale and super-resolution probability model approaches. We show the benefits of all our proposed ideas via carefully designed experiments.
One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for compressing vi
deo frames. Instead of relying on pixel-space motion (as with optical flow), our system learns deep embeddings of frames and encodes their difference in latent space. At decoder-side, an attention mechanism is designed to attend to the latent space of frames to decide how different parts of the previous and current frame are combined to form the final predicted current frame. Spatially-varying channel allocation is achieved by using importance masks acting on the feature-channels. The model is trained to reduce the bitrate by minimizing a loss on importance maps and a loss on the probability output by a context model for arithmetic coding. In our experiments, we show that the proposed system achieves high compression rates and high objective visual quality as measured by MS-SSIM and PSNR. Furthermore, we provide ablation studies where we highlight the contribution of different components.
A digital micromirror device (DMD) is an amplitude-type spatial light modulator. However, a complex-amplitude light modulation with a DMD can be achieved using the superpixel scheme. In the superpixel scheme, we notice that multiple different DMD loc
al block patterns may correspond to the same complex superpixel value. Based on this inherent encoding redundancy, a large amount of external data can be embedded into the DMD pattern without extra cost. Meanwhile, the original complex light field information carried by the DMD pattern is fully preserved. This proposed scheme is favorable for applications such as secure information transmission and copyright protection.
Due to the nonlinearity of artificial neural networks, designing topologies for deep convolutional neural networks (CNN) is a challenging task and often only heuristic approach, such as trial and error, can be applied. An evolutionary algorithm can s
olve optimization problems where the fitness landscape is unknown. However, evolutionary algorithms are computing resource intensive, which makes it difficult for problems when deep CNNs are involved. In this paper, we propose an evolutionary strategy to find better topologies for deep CNNs. Incorporating the concept of knowledge inheritance and knowledge learning, our evolutionary algorithm can be executed with limited computing resources. We applied the proposed algorithm in finding effective topologies of deep CNNs for the image classification task using CIFAR-10 dataset. After the evolution, we analyzed the topologies that performed well for this task. Our studies verify the techniques that have been commonly used in human designed deep CNNs. We also discovered that some of the graph properties greatly affect the system performance. We applied the guidelines learned from the evolution and designed new network topologies that outperform Residual Net with less layers on CIFAR-10, CIFAR-100, and SVHN dataset.
Graph clustering is an important technique to understand the relationships between the vertices in a big graph. In this paper, we propose a novel random-walk-based graph clustering method. The proposed method restricts the reach of the walking agent
using an inflation function and a normalization function. We analyze the behavior of the limited random walk procedure and propose a novel algorithm for both global and local graph clustering problems. Previous random-walk-based algorithms depend on the chosen fitness function to find the clusters around a seed vertex. The proposed algorithm tackles the problem in an entirely different manner. We use the limited random walk procedure to find attracting vertices in a graph and use them as features to cluster the vertices. According to the experimental results on the simulated graph data and the real-world big graph data, the proposed method is superior to the state-of-the-art methods in solving graph clustering problems. Since the proposed method uses the embarrassingly parallel paradigm, it can be efficiently implemented and embedded in any parallel computing environment such as a MapReduce framework. Given enough computing resources, we are capable of clustering graphs with millions of vertices and hundreds millions of edges in a reasonable time.
