arXiv subjects

Z. Jane Wang

Publications and source records attributed to Z. Jane Wang.

At least 55 records · Page 3Linked to original sources

arXiv2021

A Joint Power Splitting, Active and Passive Beamforming Optimization Framework for IRS Assisted MIMO SWIPT System

This paper considers an intelligent reflecting surface (IRS) assisted multi-input multi-output (MIMO) power splitting (PS) based simultaneous wireless information and power transfer (SWIPT) system with multiple PS receivers (PSRs). The objective is to maximize the achievable data rate of the system by jointly optimizing the PS ratios at the PSRs, the active transmit beamforming (ATB) at the access point (AP), and the passive reflective beamforming (PRB) at the IRS, while the constraints on maximum transmission power at the AP, the reflective phase shift of each element at the IRS, the individual minimum harvested energy requirement of each PSR, and the domain of PS ratio of each PSR are all satisfied. For this unsolved problem, however, since the optimization variables are intricately coupled and the constraints are conflicting, the formulated problem is non-convex, and cannot be addressed by employing exist approaches directly. To this end, we propose a joint optimization framework to solve this problem. Particularly, we reformulate it as an equivalent form by employing the Lagrangian dual transform and the fractional programming transform, and decompose the transformed problem into several sub-problems. Then, we propose an alternate optimization algorithm by capitalizing on the dual sub-gradient method, the successive convex approximation method, and the penalty-based majorization-minimization approach, to solve the sub-problems iteratively, and obtain the optimal solutions in nearly closed-forms. Numerical simulation results verify the effectiveness of the IRS in SWIPT system and indicate that the proposed algorithm offers a substantial performance gain.

cs.IT↗

arXiv2021

TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video

Estimating 3D human poses from video is a challenging problem. The lack of 3D human pose annotations is a major obstacle for supervised training and for generalization to unseen datasets. In this work, we address this problem by proposing a weakly-supervised training scheme that does not require 3D annotations or calibrated cameras. The proposed method relies on temporal information and triangulation. Using 2D poses from multiple views as the input, we first estimate the relative camera orientations and then generate 3D poses via triangulation. The triangulation is only applied to the views with high 2D human joint confidence. The generated 3D poses are then used to train a recurrent lifting network (RLN) that estimates 3D poses from 2D poses. We further apply a multi-view re-projection loss to the estimated 3D poses and enforce the 3D poses estimated from multi-views to be consistent. Therefore, our method relaxes the constraints in practice, only multi-view videos are required for training, and is thus convenient for in-the-wild settings. At inference, RLN merely requires single-view videos. The proposed method outperforms previous works on two challenging datasets, Human3.6M and MPI-INF-3DHP. Codes and pretrained models will be publicly available.

cs.CV↗

arXiv2021

Multi-view 3D Reconstruction with Transformer

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are usually investigated separately, and the object relations in different views are rarely explored. In this paper, inspired by the recent great success in self-attention-based Transformer models, we reformulate the multi-view 3D reconstruction as a sequence-to-sequence prediction problem and propose a new framework named 3D Volume Transformer (VolT) for such a task. Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network. A natural advantage of our design lies in the exploration of view-to-view relationships using self-attention among multiple unordered inputs. On ShapeNet - a large-scale 3D reconstruction benchmark dataset, our method achieves a new state-of-the-art accuracy in multi-view reconstruction with fewer parameters ($70\%$ less) than other CNN-based methods. Experimental results also suggest the strong scaling capability of our method. Our code will be made publicly available.

cs.CV↗

arXiv2021

Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models

We propose a universal and physically realizable adversarial attack on a cascaded multi-modal deep learning network (DNN), in the context of self-driving cars. DNNs have achieved high performance in 3D object detection, but they are known to be vulnerable to adversarial attacks. These attacks have been heavily investigated in the RGB image domain and more recently in the point cloud domain, but rarely in both domains simultaneously - a gap to be filled in this paper. We use a single 3D mesh and differentiable rendering to explore how perturbing the mesh's geometry and texture can reduce the robustness of DNNs to adversarial attacks. We attack a prominent cascaded multi-modal DNN, the Frustum-Pointnet model. Using the popular KITTI benchmark, we showed that the proposed universal multi-modal attack was successful in reducing the model's ability to detect a car by nearly 73%. This work can aid in the understanding of what the cascaded RGB-point cloud DNN learns and its vulnerability to adversarial attacks.

cs.CV↗

arXiv2021

A Low Complexity Quantum Principal Component Analysis Algorithm

In this paper, we propose a low complexity quantum principal component analysis (qPCA) algorithm. Similar to the state-of-the-art qPCA, it achieves dimension reduction by extracting principal components of the data matrix, rather than all components of the data matrix, to quantum registers, so that samples of measurement required can be reduced considerably. However, the major advantage of our qPCA over the state-of-the-art qPCA is that it requires much less quantum gates. In addition, it is more accurate due to the simplification of the quantum circuit. We implement the proposed qPCA on the IBM quantum computing platform, and the experimental results are consistent with our expectations.

quant-ph↗

arXiv2020

Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification

Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations imperceptible is especially challenging for transfer-based black-box adversarial attacks. Often such adversarial examples can be easily spotted due to their unpleasantly poor visual qualities, which compromises the threat of adversarial attacks in practice. In this study, to improve the image quality of black-box adversarial examples perceptually, we propose structure-aware adversarial attacks by generating adversarial images based on psychological perceptual models. Specifically, we allow higher perturbations on perceptually insignificant regions, while assigning lower or no perturbation on visually sensitive regions. In addition to the proposed spatial-constrained adversarial perturbations, we also propose a novel structure-aware frequency adversarial attack method in the discrete cosine transform (DCT) domain. Since the proposed attacks are independent of the gradient estimation, they can be directly incorporated with existing gradient-based attacks. Experimental results show that, with the comparable attack success rate (ASR), the proposed methods can produce adversarial examples with considerably improved visual quality for free. With the comparable perceptual quality, the proposed approaches achieve higher attack success rates: particularly for the frequency structure-aware attacks, the average ASR improves more than 10% over the baseline attacks.

cs.CV↗

arXiv2020

Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection

Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real face photos, promoting research on fake face detection. Though fake face forensics can achieve high detection accuracy, their anti-forensic counterparts are less investigated. Here we explore more \textit{imperceptible} and \textit{transferable} anti-forensics for fake face imagery detection based on adversarial attacks. Since facial and background regions are often smooth, even small perturbation could cause noticeable perceptual impairment in fake face images. Therefore it makes existing adversarial attacks ineffective as an anti-forensic method. Our perturbation analysis reveals the intuitive reason of the perceptual degradation issue when directly applying existing attacks. We then propose a novel adversarial attack method, better suitable for image anti-forensics, in the transformed color domain by considering visual perception. Simple yet effective, the proposed method can fool both deep learning and non-deep learning based forensic detectors, achieving higher attack success rate and significantly improved visual quality. Specially, when adversaries consider imperceptibility as a constraint, the proposed anti-forensic method can improve the average attack success rate by around 30\% on fake face images over two baseline attacks. \textit{More imperceptible} and \textit{more transferable}, the proposed method raises new security concerns to fake face imagery detection. We have released our code for public use, and hopefully the proposed method can be further explored in related forensic applications as an anti-forensic benchmark.

cs.CV↗

arXiv2020

Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss

Filtering out unrealistic images from trained generative adversarial networks (GANs) has attracted considerable attention recently. Two density ratio based subsampling methods---Discriminator Rejection Sampling (DRS) and Metropolis-Hastings GAN (MH-GAN)---were recently proposed, and their effectiveness in improving GANs was demonstrated on multiple datasets. However, DRS and MH-GAN are based on discriminator based density ratio estimation (DRE) methods, so they may not work well if the discriminator in the trained GAN is far from optimal. Moreover, they do not apply to some GANs (e.g., MMD-GAN). In this paper, we propose a novel Softplus (SP) loss for DRE. Based on it, we develop a sample-based DRE method in a feature space learned by a specially designed and pre-trained ResNet-34 (DRE-F-SP). We derive the rate of convergence of a density ratio model trained under the SP loss. Then, we propose three different density ratio subsampling methods (DRE-F-SP+RS, DRE-F-SP+MH, and DRE-F-SP+SIR) for GANs based on DRE-F-SP. Our subsampling methods do not rely on the optimality of the discriminator and are suitable for all types of GANs. We empirically show our subsampling approach can substantially outperform DRS and MH-GAN on a synthetic dataset and the CIFAR-10 dataset, using multiple GANs.

cs.LG↗

arXiv2020

CHAIN: Concept-harmonized Hierarchical Inference Interpretation of Deep Convolutional Neural Networks

With the great success of networks, it witnesses the increasing demand for the interpretation of the internal network mechanism, especially for the net decision-making logic. To tackle the challenge, the Concept-harmonized HierArchical INference (CHAIN) is proposed to interpret the net decision-making process. For net-decisions being interpreted, the proposed method presents the CHAIN interpretation in which the net decision can be hierarchically deduced into visual concepts from high to low semantic levels. To achieve it, we propose three models sequentially, i.e., the concept harmonizing model, the hierarchical inference model, and the concept-harmonized hierarchical inference model. Firstly, in the concept harmonizing model, visual concepts from high to low semantic-levels are aligned with net-units from deep to shallow layers. Secondly, in the hierarchical inference model, the concept in a deep layer is disassembled into units in shallow layers. Finally, in the concept-harmonized hierarchical inference model, a deep-layer concept is inferred from its shallow-layer concepts. After several rounds, the concept-harmonized hierarchical inference is conducted backward from the highest semantic level to the lowest semantic level. Finally, net decision-making is explained as a form of concept-harmonized hierarchical inference, which is comparable to human decision-making. Meanwhile, the net layer structure for feature learning can be explained based on the hierarchical visual concepts. In quantitative and qualitative experiments, we demonstrate the effectiveness of CHAIN at the instance and class levels.

cs.CV↗

arXiv2019

CHIP: Channel-wise Disentangled Interpretation of Deep Convolutional Neural Networks

With the widespread applications of deep convolutional neural networks (DCNNs), it becomes increasingly important for DCNNs not only to make accurate predictions but also to explain how they make their decisions. In this work, we propose a CHannel-wise disentangled InterPretation (CHIP) model to give the visual interpretation to the predictions of DCNNs. The proposed model distills the class-discriminative importance of channels in networks by utilizing the sparse regularization. Here, we first introduce the network perturbation technique to learn the model. The proposed model is capable to not only distill the global perspective knowledge from networks but also present the class-discriminative visual interpretation for specific predictions of networks. It is noteworthy that the proposed model is able to interpret different layers of networks without re-training. By combining the distilled interpretation knowledge in different layers, we further propose the Refined CHIP visual interpretation that is both high-resolution and class-discriminative. Experimental results on the standard dataset demonstrate that the proposed model provides promising visual interpretation for the predictions of networks in image classification task compared with existing visual interpretation methods. Besides, the proposed method outperforms related approaches in the application of ILSVRC 2015 weakly-supervised localization task.

cs.CV↗

arXiv2019

A Deep Learning Based Attack for The Chaos-based Image Encryption

In this letter, as a proof of concept, we propose a deep learning-based approach to attack the chaos-based image encryption algorithm in \cite{guan2005chaos}. The proposed method first projects the chaos-based encrypted images into the low-dimensional feature space, where essential information of plain images has been largely preserved. With the low-dimensional features, a deconvolutional generator is utilized to regenerate perceptually similar decrypted images to approximate the plain images in the high-dimensional space. Compared with conventional image encryption attack algorithms, the proposed method does not require to manually analyze and infer keys in a time-consuming way. Instead, we directly attack the chaos-based encryption algorithms in a key-independent manner. Moreover, the proposed method can be trained end-to-end. Given the chaos-based encrypted images, a well-trained decryption model is able to automatically reconstruct plain images with high fidelity. In the experiments, we successfully attack the chaos-based algorithm \cite{guan2005chaos} and the decrypted images are visually similar to their ground truth plain images. Experimental results on both static-key and dynamic-key scenarios verify the efficacy of the proposed method.

cs.LG↗

arXiv2019

Human Intracranial EEG Quantitative Analysis and Automatic Feature Learning for Epileptic Seizure Prediction

Objective: The aim of this study is to develop an efficient and reliable epileptic seizure prediction system using intracranial EEG (iEEG) data, especially for people with drug-resistant epilepsy. The prediction procedure should yield accurate results in a fast enough fashion to alert patients of impending seizures. Methods: We quantitatively analyze the human iEEG data to obtain insights into how the human brain behaves before and between epileptic seizures. We then introduce an efficient pre-processing method for reducing the data size and converting the time-series iEEG data into an image-like format that can be used as inputs to convolutional neural networks (CNNs). Further, we propose a seizure prediction algorithm that uses cooperative multi-scale CNNs for automatic feature learning of iEEG data. Results: 1) iEEG channels contain complementary information and excluding individual channels is not advisable to retain the spatial information needed for accurate prediction of epileptic seizures. 2) The traditional PCA is not a reliable method for iEEG data reduction in seizure prediction. 3) Hand-crafted iEEG features may not be suitable for reliable seizure prediction performance as the iEEG data varies between patients and over time for the same patient. 4) Seizure prediction results show that our algorithm outperforms existing methods by achieving an average sensitivity of 87.85% and AUC score of 0.84. Conclusion: Understanding how the human brain behaves before seizure attacks and far from them facilitates better designs of epileptic seizure predictors. Significance: Accurate seizure prediction algorithms can warn patients about the next seizure attack so they could avoid dangerous activities. Medications could then be administered to abort the impending seizure and minimize the risk of injury.

cs.NE↗

arXiv2018

DT-LET: Deep Transfer Learning by Exploring where to Transfer

Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains. This assumption doesn't always hold true, especially when the data from the two domains are heterogeneous with different resolutions. In such case, the most suitable numbers of layers for the source domain data and the target domain data would differ. As a result, the high level knowledge from the source domain would be transferred to the wrong layer of target domain. Based on this observation, "where to transfer" proposed in this paper should be a novel research frontier. We propose a new mathematic model named DT-LET to solve this heterogeneous transfer learning problem. In order to select the best matching of layers to transfer knowledge, we define specific loss function to estimate the corresponding relationship between high-level features of data in the source domain and the target domain. To verify this proposed cross-layer model, experiments for two cross-domain recognition/classification tasks are conducted, and the achieved superior results demonstrate the necessity of layer correspondence searching.

cs.LG↗

arXiv2018

Epileptic Seizure Detection: A Deep Learning Approach

Epilepsy is the second most common brain disorder after migraine. Automatic detection of epileptic seizures can considerably improve the patients' quality of life. Current Electroencephalogram (EEG)-based seizure detection systems encounter many challenges in real-life situations. The EEGs are non-stationary signals and seizure patterns vary across patients and recording sessions. Moreover, EEG data are prone to numerous noise types that negatively affect the detection accuracy of epileptic seizures. To address these challenges, we introduce the use of a deep learning-based approach that automatically learns the discriminative EEG features of epileptic seizures. Specifically, to reveal the correlation between successive data samples, the time-series EEG data are first segmented into a sequence of non-overlapping epochs. Second, Long Short-Term Memory (LSTM) network is used to learn the high-level representations of the normal and the seizure EEG patterns. Third, these representations are fed into Softmax function for training and classification. The results on a well-known benchmark clinical dataset demonstrate the superiority of the proposed approach over the existing state-of-the-art methods. Furthermore, our approach is shown to be robust in noisy and real-life conditions. Compared to current methods that are quite sensitive to noise, the proposed method maintains its high detection performance in the presence of common EEG artifacts (muscle activities and eye-blinking) as well as white noise.

eess.SP↗

arXiv2018

RAE: The Rainforest Automation Energy Dataset for Smart Grid Meter Data Analysis

Datasets are important for researchers to build models and test how well their machine learning algorithms perform. This paper presents the Rainforest Automation Energy (RAE) dataset to help smart grid researchers test their algorithms which make use of smart meter data. This initial release of RAE contains 1Hz data (mains and sub-meters) from two a residential house. In addition to power data, environmental and sensor data from the house's thermostat is included. Sub-meter data from one of the houses includes heat pump and rental suite captures which is of interest to power utilities. We also show and energy breakdown of each house and show (by example) how RAE can be used to test non-intrusive load monitoring (NILM) algorithms.

cs.OH↗

arXiv2017

Multimodal deep learning approach for joint EEG-EMG data compression and classification

In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach. Specifically, we build our system based on the deep autoencoder architecture which is designed not only to extract discriminant features in the multimodal data representation but also to reconstruct the data from the latent representation using encoder-decoder layers. Since autoencoder can be seen as a compression approach, we extend it to handle multimodal data at the encoder layer, reconstructed and retrieved at the decoder layer. We show through experimental results, that exploiting both multimodal data intercorellation and intracorellation 1) Significantly reduces signal distortion particularly for high compression levels 2) Achieves better accuracy in classifying EEG and EMG signals recorded and labeled according to the sentiments of the volunteer.

cs.LG↗

arXiv2016

Real-time 2D/3D Registration via CNN Regression

In this paper, we present a Convolutional Neural Network (CNN) regression approach for real-time 2-D/3-D registration. Different from optimization-based methods, which iteratively optimize the transformation parameters over a scalar-valued metric function representing the quality of the registration, the proposed method exploits the information embedded in the appearances of the Digitally Reconstructed Radiograph and X-ray images, and employs CNN regressors to directly estimate the transformation parameters. The CNN regressors are trained for local zones and applied in a hierarchical manner to break down the complex regression task into simpler sub-tasks that can be learned separately. Our experiment results demonstrate the advantage of the proposed method in computational efficiency with negligible degradation of registration accuracy compared to intensity-based methods.

cs.CV↗

arXiv2015

Block-Level Unitary Query: Incorporating Orthogonal-like Space-time Code with Query Diversity for MIMO Backscatter RFID

Because of the emerging field of Internet of Things (IoT), future backscatter RFID is required to be more reliable and data intensive. Motivated by this, orthogonal space-time block code (OSTBC), which is very successful in mobile communications for its low complexity and high performance, has already been investigated for backscatter RFID. On the other hand, a recently proposed scheme called unitary query was shown to be able to considerably improve the reliability of backscatter radio by exploiting query diversity. Therefore incorporating the classical OSTBC (at the tag end) with the recently proposed unitary query (at the query end) seems to be promising. However, in this paper, we show that simple, direct employment of OSTBC together with unitary query incurs a linear decoding problem and eventually leads to a severe performance degradation. As a re-design of the recently proposed unitary query and the classical OSTBC specifically for MIMO backscatter RFID, we present a BUTQ-mOSTBC design pair idea by proposing the block-level unitary query (BUTQ) at the query end and the corresponding modified OSTBC (mOSTBC) at the tag end. The proposed BUTQ-mOSTBC can resolve the linear decoding problem, keep the simplicity and high performance properties of the classical OSTBC, and achieve the query diversity for the $M \times L \times N$ MIMO backscatter RFID channel.

cs.IT↗