The essence of deep learning is to exploit data to train a deep neural network (DNN) model. This work explores the reverse process of generating data from a model, attempting to reveal the relationship between the data and the model. We repeat the process of Data to Model (DtM) and Data from Model (DfM) in sequence and explore the loss of feature mapping information by measuring the accuracy drop on the original validation dataset. We perform this experiment for both a non-robust and robust origin model. Our results show that the accuracy drop is limited even after multiple sequences of DtM and DfM, especially for robust models. The success of this cycling transformation can be attributed to the shared feature mapping existing in data and model. Using the same data, we observe that different DtM processes result in models having different features, especially for different network architecture families, even though they achieve comparable performance.
Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs) which are maliciously designed to fool target models. The normal examples (NEs) added with imperceptible adversarial perturbation, can be a security threat to DNNs. Although the existing AEs detection methods have achieved a high accuracy, they failed to exploit the information of the AEs detected. Thus, based on high-dimension perturbation extraction, we propose a model-free AEs detection method, the whole process of which is free from querying the victim model. Research shows that DNNs are sensiti…
Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）；Université Bourgogne Franche-Comté（勃艮第-弗朗什-孔泰大学）
Despite the advances in extracting local features achieved by handcrafted and learning-based descriptors, they are still limited by the lack of invariance to non-rigid transformations. In this paper, we present a new approach to compute features from still images that are robust to non-rigid deformations to circumvent the problem of matching deformable surfaces and objects. Our deformation-aware local descriptor, named DEAL, leverages a polar sampling and a spatial transformer warping to provide invariance to rotation, scale, and image deformations. We train the model architecture end-to-end b…
University of California, Berkeley（加州大学伯克利分校）；Stanford University（斯坦福大学）
This is an extended abstract for a presentation at The 17th International Conference on CUPUM - Computational Urban Planning and Urban Management in June 2021. This study presents an interdisciplinary synthesis of the state-of-the-art approaches in computer vision technologies to extract built environment features that could improve the robustness of empirical research in planning. We discussed the findings from the review of studies in both planning and computer science.
Face recognition systems must be robust to the variation of various factors such as facial expression, illumination, head pose and aging. Especially, the robustness against illumination variation is one of the most important problems to be solved for the practical use of face recognition systems. Gabor wavelet is widely used in face detection and recognition because it gives the possibility to simulate the function of human visual system. In this paper, we propose a method for extracting Gabor wavelet features which is stable under the variation of local illumination and show experiment result…
Pakistan Institute of Engineering and Applied Sciences（巴基斯坦工程与应用科学学院）；PIEAS Artificial Intelligence Center (PAIC)（PIEAS人工智能中心）
Higgs boson is a fundamental particle, and the classification of Higgs signals is a well-known problem in high energy physics. The identification of the Higgs signal is a challenging task because its signal has a resemblance to the background signals. This study proposes a Higgs signal classification using a novel combination of random forest, auto encoder and deep auto encoder to build a robust and generalized Higgs boson prediction system to discriminate the Higgs signal from the background noise. The proposed ensemble technique is based on achieving diversity in the decision space, and the …
A variety of operations of cellular automata on gray images is presented. All operations are of a wave-front nature finishing in a stable state. They are used to extract shape descripting gray objects robust to a variety of pattern distortions. Topographic terms are used: "lakes", "dales", "dales of dales". It is shown how mutual object relations like "above" can be presented in terms of gray image analysis and how it can be used for character classification and for gray pattern decomposition. Algorithms can be realized with a parallel asynchronous architecture. Keywords: Pattern Recognition, …
Convolutional Neural Networks have become the norm in image classification. Nevertheless, their difficulty to maintain high accuracy across datasets has become apparent in the past few years. In order to utilize such models in real-world scenarios and applications, they must be able to provide trustworthy predictions on unseen data. In this paper, we argue that extracting features from a CNN's intermediate layers can assist in the model's final prediction. Specifically, we adapt the Hypercolumns method to a ResNet-18 and find a significant increase in the model's accuracy, when evaluating on t…
Polish-Japanese Academy of Information Technology（波兰日本信息技术学院）；Tooploox（Tooploox公司）；Warsaw University of Technology（华沙理工大学）
Textual overlays are often used in social media videos as people who watch them without the sound would otherwise miss essential information conveyed in the audio stream. This is why extraction of those overlays can serve as an important meta-data source, e.g. for content classification or retrieval tasks. In this work, we present a robust method for extracting textual overlays from videos that builds up on multiple neural network architectures. The proposed solution relies on several processing steps: keyframe extraction, text detection and text recognition. The main component of our system, …
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features. This motivates us to preserve both robust and non-robust features and separate them with disentangled representation learning. Our proposed Adversarial Asymmetric Training (AAT) algorithm can reliably disentangle robust and non-robust representations without additional supervision on robustness. Empirical results show our meth…
USDA-ARS-AFRS（美国农业部农业研究局农业研究服务局（USDA-ARS-AFRS））；Marquette University（马凯特大学）；Electrical and Computer Engineering（电气与计算机工程（此处为系，按规则不提取，仅保留大学））；Kearneysville, West Virginia, USA（美国西弗吉尼亚州卡尼尔斯维尔（地址，不提取））；Milwaukee, Wisconsin, USA（美国威斯康星州密尔沃基（地址，不提取））
We consider the problem of extracting curve skeletons of three-dimensional, elongated objects given a noisy surface, which has applications in agricultural contexts such as extracting the branching structure of plants. We describe an efficient and robust method based on breadth-first search that can determine curve skeletons in these contexts. Our approach is capable of automatically detecting junction points as well as spurious segments and loops. All of that is accomplished with only one user-adjustable parameter. The run time of our method ranges from hundreds of milliseconds to less than f…
Indian Institute of Technology Kharagpur（印度理工学院克勒格布尔分校）
Facial expression recognition has many potential applications which has attracted the attention of researchers in the last decade. Feature extraction is one important step in expression analysis which contributes toward fast and accurate expression recognition. This paper represents an approach of combining the shape and appearance features to form a hybrid feature vector. We have extracted Pyramid of Histogram of Gradients (PHOG) as shape descriptors and Local Binary Patterns (LBP) as appearance features. The proposed framework involves a novel approach of extracting hybrid features from acti…
Photoplethysmographic imaging is a camera-based solution for non-contact cardiovascular monitoring from a distance. This technology enables monitoring in situations where contact-based devices may be problematic or infeasible, such as ambulatory, sleep, and multi-individual monitoring. However, extracting the blood pulse waveform signal is challenging due to the unknown mixture of relevant (pulsatile) and irrelevant pixels in the scene. Here, we design and implement a signal fusion framework, FusionPPG, for extracting a blood pulse waveform signal with strong temporal fidelity from a scene wit…
Alibaba Group（阿里巴巴集团）；University of Electronic Science and Technology of China（电子科技大学）；University of Technology Sydney（悉尼科技大学）；Nanjing University of Science and Technology（南京理工大学）
Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive research has been devoted to the first two, but much less attention has been paid to the third. Due to the high cost of manual labeling, the size of recent efforts such as ImageNet is still relatively small in respect to daily applications. In this work, we mainly focus on how to automatically generate identifying image data for a given visual concept on a vast scale. With the generated image data, we can train a rob…
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）
Digital image watermarking is the process of embedding and extracting watermark covertly on a carrier image. Incorporating deep learning networks with image watermarking has attracted increasing attention during recent years. However, existing deep learning-based watermarking systems cannot achieve robustness, blindness, and automated embedding and extraction simultaneously. In this paper, a fully automated image watermarking system based on deep neural networks is proposed to generalize the image watermarking processes. An unsupervised deep learning structure and a novel loss computation are …
Extracting class activation maps (CAM) from a classification model often results in poor coverage on foreground objects, i.e., only the discriminative region (e.g., the "head" of "sheep") is recognized and the rest (e.g., the "leg" of "sheep") mistakenly as background. The crux behind is that the weight of the classifier (used to compute CAM) captures only the discriminative features of objects. We tackle this by introducing a new computation method for CAM that explicitly captures non-discriminative features as well, thereby expanding CAM to cover whole objects. Specifically, we omit the last…
Constrained Optimization solution algorithms are restricted to point based solutions. In practice, single or multiple objectives must be satisfied, wherein both the objective function and constraints can be non-convex resulting in multiple optimal solutions. Real world scenarios include intersecting surfaces as Implicit Functions, Hyperspectral Unmixing and Pareto Optimal fronts. Local or global convexification is a common workaround when faced with non-convex forms. However, such an approach is often restricted to a strict class of functions, deviation from which results in sub-optimal soluti…
