Preprocessing defenses such as pixel discretization are appealing to remove adversarial attacks due to their simplicity. However, they have been shown to be ineffective except on simple datasets like MNIST. We hypothesize that existing discretization approaches failed because using a fixed codebook for the entire dataset limits their ability to balance image representation and codeword separability. We first formally prove that adaptive codebooks can provide stronger robustness guarantees than fixed codebooks as a preprocessing defense on some datasets. Based on that insight, we propose a content-adaptive pixel discretization defense called Essential Features, which discretizes the image to a per-image adaptive codebook to reduce the color space. We then find that Essential Features can be further optimized by applying adaptive blurring before the discretization to push perturbed pixel values back to their original value before determining the codebook. Against adaptive attacks, we show that content-adaptive pixel discretization extends the range of datasets that benefit in terms of both L_2 and L_infinity robustness where previously fixed codebooks were found to have failed. Our findings suggest that content-adaptive pixel discretization should be part of the repertoire for making models robust.
Google（谷歌）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly attractive in practice due to their simplicity, low computational overhead, and applicability to various systems. It is observed that such methods work well on simple datasets like MNIST, but break on more complicated ones like ImageNet under recently proposed strong white-box attacks. To understand the conditions for success and potentials for improvement, we study the pixel d…
Stony Brook University（石溪大学）；University of Michigan（密歇根大学）
Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear normal to human beings. Recent work has shown that pixel discretization can be used to make classifiers for MNIST highly robust to adversarial examples. However, pixel discretization fails to provide significant protection on more complex datasets. In this paper, we take the first step towards reconciling these contrary findings. Focusing on the observation that discrete pixelization in MNIST makes the background comp…
Adversarial examples are perturbed inputs that are designed (from a deep learning network's (DLN) parameter gradients) to mislead the DLN during test time. Intuitively, constraining the dimensionality of inputs or parameters of a network reduces the 'space' in which adversarial examples exist. Guided by this intuition, we demonstrate that discretization greatly improves the robustness of DLNs against adversarial attacks. Specifically, discretizing the input space (or allowed pixel levels from 256 values or 8-bit to 4 values or 2-bit) extensively improves the adversarial robustness of DLNs for …
Microsoft Corporation（微软公司）；Stanford University（斯坦福大学）
Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each pixel, and then feed the result into any pre-trained classifier. Theoretically, we show that our randomized discretization strategy reduces the KL divergence between original and adversarial inputs, leading to a lower bound on the classification accuracy of any classifier against any (potentially whitebox) $\ell_\infty$-bounded adversarial attack. Empirical…
Purdue University（普渡大学）；Politecnico di Milano（米兰理工大学）
Manipulating video content is easier than ever. Due to the misuse potential of manipulated content, multiple detection techniques that analyze the pixel data from the videos have been proposed. However, clever manipulators should also carefully forge the metadata and auxiliary header information, which is harder to do for videos than images. In this paper, we propose to identify forged videos by analyzing their multimedia stream descriptors with simple binary classifiers, completely avoiding the pixel space. Using well-known datasets, our results show that this scalable approach can achieve a …
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Style-guided text image generation tries to synthesize text image by imitating reference image's appearance while keeping text content unaltered. The text image appearance includes many aspects. In this paper, we focus on transferring style image's background and foreground color patterns to the content image to generate photo-realistic text image. To achieve this goal, we propose 1) a content-style cross attention based pixel sampling approach to roughly mimicking the style text image's background; 2) a pixel-wise style modulation technique to transfer varying color patterns of the style imag…
The goal of video highlight detection is to select the most attractive segments from a long video to depict the most interesting parts of the video. Existing methods typically focus on modeling relationship between different video segments in order to learning a model that can assign highlight scores to these segments; however, these approaches do not explicitly consider the contextual dependency within individual segments. To this end, we propose to learn pixel-level distinctions to improve the video highlight detection. This pixel-level distinction indicates whether or not each pixel in one …
An accurate method for warping images is presented. Differently from most commonly used techniques, this method guarantees the conservation of the intensity of the transformed image, evaluated as the sum of its pixel values over the whole image or over corresponding transformed subregions of it. Such property is mandatory for quantitative analysis, as, for instance, when deformed images are used to assess radiances, to measure optical fluxes from light sources, or to characterize material optical densities. The proposed method enforces area resampling by decomposing each rectangular pixel in t…
A patch-based non-local restoration and reconstruction method for preprocessing degraded document images is introduced. The method collects relative data from the whole input image, while the image data are first represented by a content-level descriptor based on patches. This patch-equivalent representation of the input image is then corrected based on similar patches identified using a modified genetic algorithm (GA) resulting in a low computational load. The corrected patch-equivalent is then converted to the output restored image. The fact that the method uses the patches at the content le…
This paper considers how to separate text and/or graphics from smooth background in screen content and mixed document images and proposes two approaches to perform this segmentation task. The proposed methods make use of the fact that the background in each block is usually smoothly varying and can be modeled well by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity. The algorithms separate the background and foreground pixels by trying to fit background pixel values in the block into a smooth function using two di…
Convolutional neural networks (CNNs) have been not only widespread but also achieved noticeable results on numerous applications including image classification, restoration, and generation. Although the weight-sharing property of convolutions makes them widely adopted in various tasks, its content-agnostic characteristic can also be considered a major drawback. To solve this problem, in this paper, we propose a novel operation, called pixel adaptive kernel attention (PAKA). PAKA provides directivity to the filter weights by multiplying spatially varying attention from learnable features. The p…
University of Amsterdam（阿姆斯特丹大学）；Tilburg University（蒂尔堡大学）
In this work we propose Pixel Content Encoders (PCE), a light-weight image inpainting model, capable of generating novel con-tent for large missing regions in images. Unlike previously presented convolutional neural network based models, our PCE model has an order of magnitude fewer trainable parameters. Moreover, by incorporating dilated convolutions we are able to preserve fine grained spatial information, achieving state-of-the-art performance on benchmark datasets of natural images and paintings. Besides image inpainting, we show that without changing the architecture, PCE can be used for …
University College London（伦敦大学学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Imperial College London（帝国理工学院）
State-of-the-art methods for computer vision rely heavily on the translation equivariance and spatial sharing properties of convolutional layers without explicitly taking into consideration the input content. Modern techniques employ deep sophisticated architectures in order to circumvent this issue. In this work, we propose a Pixel Adaptive Filtering Unit (PAFU) which introduces a differentiable kernel selection mechanism paired with a discrete, learnable and decorrelated group of kernels to allow for content-based spatial adaptation. First, we demonstrate the applicability of the technique i…
Efficient and easy segmentation of images and volumes is of great practical importance. Segmentation problems that motivate our approach originate from microscopy imaging commonly used in materials science, medicine, and biology. We formulate image segmentation as a probabilistic pixel classification problem, and we apply segmentation as a step towards characterising image content. Our method allows the user to define structures of interest by interactively marking a subset of pixels. Thanks to the real-time feedback, the user can place new markings strategically, depending on the current outc…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing. In the proposed screen scaling scheme, a screen content classification step is first introduced to classify the screen image into text and pictorial regions. Afterward, we propose an adaptive shift linear interpolation algorithm to predict the new pixel values with the shift offset adapted to the content type of each pixel. The shift offset for each screen content type is offline optimized by minimizing the theoretical interpolation error b…
University of Michigan（密歇根大学）；Adobe Research（Adobe 研究院）；POSTECH（浦项科技大学）；Beihang University（北京航空航天大学）；Google Brain（谷歌大脑）
We propose a deep neural network for the prediction of future frames in natural video sequences. To effectively handle complex evolution of pixels in videos, we propose to decompose the motion and content, two key components generating dynamics in videos. Our model is built upon the Encoder-Decoder Convolutional Neural Network and Convolutional LSTM for pixel-level prediction, which independently capture the spatial layout of an image and the corresponding temporal dynamics. By independently modeling motion and content, predicting the next frame reduces to converting the extracted content feat…
The University of Tennessee Knoxville（田纳西大学诺克斯维尔分校）
Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Forensic Anthropology. We leverage the evolving nature of images depicting the decay process in human decomposition data to design a simple yet effective pseudo-pixel-level label generation technique to reduce the amount of effort for manual annotation of such images. We first identify sequences of images with a minimum variation that are most suitable to share the same or similar annotation using an unsupervised approac…
University of Notre Dame（圣母大学）；University of Campinas（坎皮纳斯大学）
Creative works, whether paintings or memes, follow unique journeys that result in their final form. Understanding these journeys, a process known as "provenance analysis", provides rich insights into the use, motivation, and authenticity underlying any given work. The application of this type of study to the expanse of unregulated content on the Internet is what we consider in this paper. Provenance analysis provides a snapshot of the chronology and validity of content as it is uploaded, re-uploaded, and modified over time. Although still in its infancy, automated provenance analysis for onlin…
University of Nebraska at Omaha（内布拉斯加大学奥马哈分校）；New Jersey Institute of Technology（新泽西理工学院）
Image segmentation as a clustering problem is to identify pixel groups on an image without any preliminary labels available. It remains a challenge in machine vision because of the variations in size and shape of image segments. Furthermore, determining the segment number in an image is NP-hard without prior knowledge of the image content. This paper presents an automatic color image pixel clustering scheme based on mussels wandering optimization. By applying an activation variable to determine the number of clusters along with the cluster centers optimization, an image is segmented with minim…
This paper proposes a representational model for image pairs such as consecutive video frames that are related by local pixel displacements, in the hope that the model may shed light on motion perception in primary visual cortex (V1). The model couples the following two components: (1) the vector representations of local contents of images and (2) the matrix representations of local pixel displacements caused by the relative motions between the agent and the objects in the 3D scene. When the image frame undergoes changes due to local pixel displacements, the vectors are multiplied by the matri…
The improvement of the accuracy of image query retrieval used image classification technique. Image classification is well known technique of supervised learning. The improved method of image classification increases the working efficiency of image query retrieval. For the improvements of classification technique we used RBF neural network function for better prediction of feature used in image retrieval.Colour content is represented by pixel values in image classification using radial base function(RBF) technique. This approach provides better result compare to SVM technique in image represen…
This paper considers how to separate text and/or graphics from smooth background in screen content and mixed content images and proposes an algorithm to perform this segmentation task. The proposed methods make use of the fact that the background in each block is usually smoothly varying and can be modeled well by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity. This algorithm separates the background and foreground pixels by trying to fit pixel values in the block into a smooth function using a robust regression…
New York University（纽约大学）；Huawei Technologies（华为技术有限公司）
Background/foreground segmentation has a lot of applications in image and video processing. In this paper, a segmentation algorithm is proposed which is mainly designed for text and line extraction in screen content. The proposed method makes use of the fact that the background in each block is usually smoothly varying and can be modeled well by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity. The algorithm separates the background and foreground pixels by trying to fit pixel values in the block into a smooth fun…
We introduce an approach to generating videos based on a series of given language descriptions. Frames of the video are generated sequentially and optimized by guidance from the CLIP image-text encoder; iterating through language descriptions, weighting the current description higher than others. As opposed to optimizing through an image generator model itself, which tends to be computationally heavy, the proposed approach computes the CLIP loss directly at the pixel level, achieving general content at a speed suitable for near real-time systems. The approach can generate videos in up to 720p …
Layout is essential for graphic design and poster generation. Recently, applying deep learning models to generate layouts has attracted increasing attention. This paper focuses on using the GAN-based model conditioned on image contents to generate advertising poster graphic layouts, which requires an advertising poster layout dataset with paired product images and graphic layouts. However, the paired images and layouts in the existing dataset are collected by inpainting and annotating posters, respectively. There exists a domain gap between inpainted posters (source domain data) and clean prod…
Video compression is a critical component of Internet video delivery. Recent work has shown that deep learning techniques can rival or outperform human-designed algorithms, but these methods are significantly less compute and power-efficient than existing codecs. This paper presents a new approach that augments existing codecs with a small, content-adaptive super-resolution model that significantly boosts video quality. Our method, SRVC, encodes video into two bitstreams: (i) a content stream, produced by compressing downsampled low-resolution video with the existing codec, (ii) a model stream…
Nowadays, online screen sharing and remote cooperation are becoming ubiquitous. However, the screen content may be downsampled and compressed during transmission, while it may be displayed on large screens or the users would zoom in for detail observation at the receiver side. Therefore, developing a strong and effective screen content image (SCI) super-resolution (SR) method is demanded. We observe that the weight-sharing upsampler (such as deconvolution or pixel shuffle) could be harmful to sharp and thin edges in SCIs, and the fixed scale upsampler makes it inflexible to fit screens with va…
Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects. We present a method for training a convolutional neural network such that it takes in an input image and produces a full graph definition. This is done end-to-end in a single stage with the use of associative embeddings. The network learns to simultaneously identify all of the elements that make up a graph and piece them together. We benchmark on the Visual Genome dataset, and demonstrate state-of-the-art per…
MPI-CBG/PKS (CSBD)（马克斯·普朗克分子细胞生物学与遗传学研究所/普朗克计算生物学中心（德累斯顿系统生物学中心））；Brno University of Technology（布尔诺理工大学）
Today, Convolutional Neural Networks (CNNs) are the leading method for image denoising. They are traditionally trained on pairs of images, which are often hard to obtain for practical applications. This motivates self-supervised training methods such as Noise2Void~(N2V) that operate on single noisy images. Self-supervised methods are, unfortunately, not competitive with models trained on image pairs. Here, we present 'Probabilistic Noise2Void' (PN2V), a method to train CNNs to predict per-pixel intensity distributions. Combining these with a suitable description of the noise, we obtain a compl…
University of California, Merced（加州大学默塞德分校）；Adobe Research（Adobe研究院）
In this paper, we propose an effective face completion algorithm using a deep generative model. Different from well-studied background completion, the face completion task is more challenging as it often requires to generate semantically new pixels for the missing key components (e.g., eyes and mouths) that contain large appearance variations. Unlike existing nonparametric algorithms that search for patches to synthesize, our algorithm directly generates contents for missing regions based on a neural network. The model is trained with a combination of a reconstruction loss, two adversarial los…
Recently, a series of works in computer vision have shown promising results on various image and video understanding tasks using self-attention. However, due to the quadratic computational and memory complexities of self-attention, these works either apply attention only to low-resolution feature maps in later stages of a deep network or restrict the receptive field of attention in each layer to a small local region. To overcome these limitations, this work introduces a new global self-attention module, referred to as the GSA module, which is efficient enough to serve as the backbone component…
Microsoft Research Asia（微软亚洲研究院）；Xi’an Jiaotong University（西安交通大学）；Microsoft Research（微软研究院）
Image enhancement aims at improving the aesthetic visual quality of photos by retouching the color and tone, and is an essential technology for professional digital photography. Recent years deep learning-based image enhancement algorithms have achieved promising performance and attracted increasing popularity. However, typical efforts attempt to construct a uniform enhancer for all pixels' color transformation. It ignores the pixel differences between different content (e.g., sky, ocean, etc.) that are significant for photographs, causing unsatisfactory results. In this paper, we propose a no…
In this paper a fast triangular mesh based registration method is proposed. Having Template and Reference images as inputs, the template image is triangulated using a content adaptive mesh generation algorithm. Considering the pixel values at mesh nodes, interpolated using spline interpolation method for both of the images, the energy functional needed for image registration is minimized. The minimization process was achieved using a mesh based discretization of the distance measure and regularization term which resulted in a sparse system of linear equations, which due to the smaller size in …
Nowadays, there is an explosive growth of screen contents due to the wide application of screen sharing, remote cooperation, and online education. To match the limited terminal bandwidth, high-resolution (HR) screen contents may be downsampled and compressed. At the receiver side, the super-resolution (SR) of low-resolution (LR) screen content images (SCIs) is highly demanded by the HR display or by the users to zoom in for detail observation. However, image SR methods mostly designed for natural images do not generalize well for SCIs due to the very different image characteristics as well as …
The ability to characterize the color content of natural imagery is an important application of image processing. The pixel by pixel coloring of images may be viewed naturally as points in color space, and the inherent structure and distribution of these points affords a quantization, through clustering, of the color information in the image. In this paper, we present a novel topologically driven clustering algorithm that permits segmentation of the color features in a digital image. The algorithm blends Locally Linear Embedding (LLE) and vector quantization by mapping color information to a l…
Distributed visual analysis applications, such as mobile visual search or Visual Sensor Networks (VSNs) require the transmission of visual content on a bandwidth-limited network, from a peripheral node to a processing unit. Traditionally, a Compress-Then-Analyze approach has been pursued, in which sensing nodes acquire and encode the pixel-level representation of the visual content, that is subsequently transmitted to a sink node in order to be processed. This approach might not represent the most effective solution, since several analysis applications leverage a compact representation of the …
Convolutions are the fundamental building block of CNNs. The fact that their weights are spatially shared is one of the main reasons for their widespread use, but it also is a major limitation, as it makes convolutions content agnostic. We propose a pixel-adaptive convolution (PAC) operation, a simple yet effective modification of standard convolutions, in which the filter weights are multiplied with a spatially-varying kernel that depends on learnable, local pixel features. PAC is a generalization of several popular filtering techniques and thus can be used for a wide range of use cases. Spec…
