Arrow Research search

Author name cluster

Z. Jane Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers
1 author row

Possible papers

15

NeurIPS Conference 2024 Conference Paper

AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks

  • Jin Li
  • Ziqiang He
  • Anwei Luo
  • Jian-Fang Hu
  • Z. Jane Wang
  • Xiangui Kang

Imperceptible adversarial attacks aim to fool DNNs by adding imperceptible perturbation to the input data. Previous methods typically improve the imperceptibility of attacks by integrating common attack paradigms with specifically designed perception-based losses or the capabilities of generative models. In this paper, we propose Adversarial Attacks in Diffusion (AdvAD), a novel modeling framework distinct from existing attack paradigms. AdvAD innovatively conceptualizes attacking as a non-parametric diffusion process by theoretically exploring basic modeling approach rather than using the denoising or generation abilities of regular diffusion models requiring neural networks. At each step, much subtler yet effective adversarial guidance is crafted using only the attacked model without any additional network, which gradually leads the end of diffusion process from the original image to a desired imperceptible adversarial example. Grounded in a solid theoretical foundation of the proposed non-parametric diffusion process, AdvAD achieves high attack efficacy and imperceptibility with intrinsically lower overall perturbation strength. Additionally, an enhanced version AdvAD-X is proposed to evaluate the extreme of our novel framework under an ideal scenario. Extensive experiments demonstrate the effectiveness of the proposed AdvAD and AdvAD-X. Compared with state-of-the-art imperceptible attacks, AdvAD achieves an average of 99. 9% (+17. 3%) ASR with 1. 34 (-0. 97) $l_2$ distance, 49. 74 (+4. 76) PSNR and 0. 9971 (+0. 0043) SSIM against four prevalent DNNs with three different architectures on the ImageNet-compatible dataset. Code is available at https: //github. com/XianguiKang/AdvAD.

PDF Details DOI

AAAI Conference 2024 Conference Paper

PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF

  • Mohsen Gholami
  • Rabab Ward
  • Z. Jane Wang

This paper proposes an end-to-end framework for generating 3D human pose datasets using Neural Radiance Fields (NeRF). Public datasets generally have limited diversity in terms of human poses and camera viewpoints, largely due to the resource-intensive nature of collecting 3D human pose data. As a result, pose estimators trained on public datasets significantly underperform when applied to unseen out-of-distribution samples. Previous works proposed augmenting public datasets by generating 2D-3D pose pairs or rendering a large amount of random data. Such approaches either overlook image rendering or result in suboptimal datasets for pre-trained models. Here we propose PoseGen, which learns to generate a dataset (human 3D poses and images) with a feedback loss from a given pre-trained pose estimator. In contrast to prior art, our generated data is optimized to improve the robustness of the pre-trained model. The objective of PoseGen is to learn a distribution of data that maximizes the prediction error of a given pre-trained model. As the learned data distribution contains OOD samples of the pre-trained model, sampling data from such a distribution for further fine-tuning a pre-trained model improves the generalizability of the model. This is the first work that proposes NeRFs for 3D human data generation. NeRFs are data-driven and do not require 3D scans of humans. Therefore, using NeRF for data generation is a new direction for convenient user-specific data generation. Our extensive experiments show that the proposed PoseGen improves two baseline models (SPIN and HybrIK) on four datasets with an average 6% relative improvement.

PDF Details DOI

JBHI Journal 2021 Journal Article

Bridging the Gap Between 2D and 3D Contexts in CT Volume for Liver and Tumor Segmentation

  • Lei Song
  • Haoqian Wang
  • Z. Jane Wang

Automatic liver and tumor segmentation remain a challenging topic, which subjects to the exploration of 2D and 3D contexts in CT volume. Existing methods are either only focus on the 2D context by treating the CT volume as many independent image slices (but ignore the useful temporal information between adjacent slices), or just explore the 3D context lied in many little voxels (but damage the spatial detail in each slice). These factors lead an inadequate context exploration together for automatic liver and tumor segmentation. In this paper, we propose a novel full-context convolution neural network to bridge the gap between 2D and 3D contexts. The proposed network can utilize the temporal information along the Z axis in CT volume while retaining the spatial detail in each slice. Specifically, a 2D spatial network for intra-slice features extraction and a 3D temporal network for inter-slice features extraction are proposed separately and then are guided by the squeeze-and-excitation layer that allows the flow of 2D context and 3D temporal information. To address the severe class imbalance issue in the CT volume and meanwhile improve the segmentation performance, a loss function consisting of weighted cross-entropy and jaccard distance is proposed. During the network training, the 2D and 3D contexts are learned jointly in an end-to-end way. The proposed network achieves competitive results on the Liver Tumor Segmentation Challenge (LiTS) and the 3D-IRCADB datasets. This method should be a new promising paradigm to explore the contexts for liver and tumor segmentation.

Details DOI

AAAI Conference 2021 Conference Paper

Towards Universal Physical Attacks on Single Object Tracking

  • Li Ding
  • Yongwei Wang
  • Kaiwen Yuan
  • Minyang Jiang
  • Ping Wang
  • Hua Huang
  • Z. Jane Wang

Recent studies show that small perturbations in video frames could misguide single object trackers. However, such attacks have been mainly designed for digital-domain videos (i. e. , perturbation on full images), which makes them practically infeasible to evaluate the adversarial vulnerability of trackers in real-world scenarios. Here we made the first step towards physically feasible adversarial attacks against visual tracking in real scenes with a universal patch to camouflage single object trackers. Fundamentally different from physical object detection, the essence of single object tracking lies in the feature matching between the search image and templates, and we therefore specially design the maximum textural discrepancy (MTD), a resolution-invariant and target location-independent feature de-matching loss. The MTD distills global textural information of the template and search images at hierarchical feature scales prior to performing feature attacks. Moreover, we evaluate two shape attacks, the regression dilation and shrinking, to generate stronger and more controllable attacks. Further, we employ a set of transformations to simulate diverse visual tracking scenes in the wild. Experimental results show the effectiveness of the physically feasible attacks on SiamMask and SiamRPN++ visual trackers both in digital and physical scenes.

PDF Details

JBHI Journal 2020 Journal Article

An End-to-End Multi-Task Deep Learning Framework for Skin Lesion Analysis

  • Lei Song
  • Jianzhe Lin
  • Z. Jane Wang
  • Haoqian Wang

Automatic skin lesion analysis of dermoscopy images remains a challenging topic. In this paper, we propose an end-to-end multi-task deep learning framework for automatic skin lesion analysis. The proposed framework can perform skin lesion detection, classification, and segmentation tasks simultaneously. To address the class imbalance issue in the dataset (as often observed in medical image datasets) and meanwhile to improve the segmentation performance, a loss function based on the focal loss and the jaccard distance is proposed. During the framework training, we employ a three-phase joint training strategy to ensure the efficiency of feature learning. The proposed framework outperforms state-of-the-art methods on the benchmarks ISBI 2016 challenge dataset towards melanoma classification and ISIC 2017 challenge dataset towards melanoma segmentation, especially for the segmentation task. The proposed framework should be a promising computer-aided tool for melanoma diagnosis.

Details DOI

JBHI Journal 2019 Journal Article

Dynamic Graph Theoretical Analysis of Functional Connectivity in Parkinson's Disease: The Importance of Fiedler Value

  • Jiayue Cai
  • Aiping Liu
  • Taomian Mi
  • Saurabh Garg
  • Wade Trappe
  • Martin J. McKeown
  • Z. Jane Wang

Graph theoretical analysis is a powerful tool for quantitatively evaluating brain connectivity networks. Conventionally, brain connectivity is assumed to be temporally stationary, whereas increasing evidence suggests that functional connectivity exhibits temporal variations during dynamic brain activity. Although a number of methods have been developed to estimate time-dependent brain connectivity, there is a paucity of studies examining the utility of brain dynamics for assessing brain disease states. Therefore, this paper aims to assess brain connectivity dynamics in Parkinson's disease (PD) and determine the utility of such dynamic graph measures as potential components to an imaging biomarker. Resting-state functional magnetic resonance imaging data were collected from 29 healthy controls and 69 PD subjects. Time-varying functional connectivity was first estimated using a sliding windowed sparse inverse covariance matrix. Then, a collection of graph measures, including the Fiedler value, were computed and the dynamics of the graph measures were investigated. The results demonstrated that PD subjects had a lower variability in the Fiedler value, modularity, and global efficiency, indicating both abnormal dynamic global integration and local segregation of brain networks in PD. Autoregressive models fitted to the dynamic graph measures suggested that Fiedler value, characteristic path length, global efficiency, and modularity were all less deterministic in PD. With canonical correlation analysis, the altered dynamics of functional connectivity networks, and particularly dynamic Fiedler value, were shown to be related with disease severity and other clinical variables including age. Similarly, Fiedler value was the most important feature for classification. Collectively, our findings demonstrate altered dynamic graph properties, and in particular the Fiedler value, provide an additional dimension upon which to non-invasively and quantitatively assess PD.

Details DOI

JBHI Journal 2017 Journal Article

Automated Detection and Segmentation of Vascular Structures of Skin Lesions Seen in Dermoscopy, With an Application to Basal Cell Carcinoma Classification

  • Pegah Kharazmi
  • Mohammed I. AlJasser
  • Harvey Lui
  • Z. Jane Wang
  • Tim K. Lee

Blood vessels are important biomarkers in skin lesions both diagnostically and clinically. Detection and quantification of cutaneous blood vessels provide critical information toward lesion diagnosis and assessment. In this paper, a novel framework for detection and segmentation of cutaneous vasculature from dermoscopy images is presented and the further extracted vascular features are explored for skin cancer classification. Given a dermoscopy image, we segment vascular structures of the lesion by first decomposing the image using independent component analysis into melanin and hemoglobin components. This eliminates the effect of pigmentation on the visibility of blood vessels. Using k-means clustering, the hemoglobin component is then clustered into normal, pigmented, and erythema regions. Shape filters are then applied to the erythema cluster at different scales. A vessel mask is generated as a result of global thresholding. The segmentation sensitivity and specificity of 90% and 86% were achieved on a set of 500 000 manually segmented pixels provided by an expert. To further demonstrate the superiority of the proposed method, based on the segmentation results, we defined and extracted vascular features toward lesion diagnosis in basal cell carcinoma (BCC). Among a dataset of 659 lesions (299 BCC and 360 non-BCC), a set of 12 vascular features are extracted from the final vessel images of the lesions and fed into a random forest classifier. When compared with a few other state-of-art methods, the proposed method achieves the best performance of 96. 5% in terms of area under the curve (AUC) in differentiating BCC from benign lesions using only the extracted vascular features.

Details DOI

JBHI Journal 2017 Journal Article

Illumination Variation-Resistant Video-Based Heart Rate Measurement Using Joint Blind Source Separation and Ensemble Empirical Mode Decomposition

  • Juan Cheng
  • Xun Chen
  • Lingxi Xu
  • Z. Jane Wang

Recent studies have demonstrated that heart rate (HR) could be estimated using video data [e. g. , exploring human facial regions of interest (ROIs)] under wellcontrolled conditions. However, in practice, the pulse signals may be contaminated by motions and illumination variations. In this paper, tackling the illumination variation challenge, we propose an illumination-robust framework using joint blind source separation (JBSS) and ensemble empirical mode decomposition (EEMD) to effectively evaluate HR from webcam videos. The framework takes the hypotheses that both facial ROI and background ROI have similar illumination variations. The background ROI is then considered as a noise reference sensor to denoise the facial signals by using the JBSS technique to extract the underlying illumination variation sources. Further, the reconstructed illumination-resisted green channel of the facial ROI is detrended and decomposed into a number of intrinsic mode functions using EEMD to estimate the HR. Experimental results demonstrated that the proposed framework could estimate HR more accurately than the state-of-the-art methods. The Bland-Altman plots showed that it led to better agreement with HR ground truth with the mean bias 1. 15 beats/min (bpm), with 95% limits from -15. 43 to 17. 73 bpm, and the correlation coefficient 0. 53. This study provides a promising solution for realistic noncontact and robust HR measurement applications.

Details DOI

JBHI Journal 2014 Journal Article

A Three-Step Multimodal Analysis Framework for Modeling Corticomuscular Activity With Application to Parkinson’s Disease

  • Xun Chen
  • Z. Jane Wang
  • Martin J. McKeown

Corticomuscular coupling analysis based on multiple datasets such as electroencephalography (EEG) and electromyography (EMG) signals provides a useful tool for understanding human motor control systems. A popular conventional method to assess corticomuscular coupling has been the pair-wise magnitude-squared coherence (MSC) between EEG and concomitant EMG recordings. However, there are certain limitations associated with the MSC, including the difficulty in robustly assessing group inference, only dealing with two types of datasets simultaneously and the biologically implausible assumption of pair-wise interactions. To overcome such limitations, in this paper, we propose assessing corticomuscular coupling by combining multiset canonical correlation analysis (M-CCA) and joint independent component analysis (jICA). The proposed method takes advantage of the M-CCA and jICA to ensure that the extracted components are maximally correlated across multiple datasets and meanwhile statistically independent within each dataset. Simulations were performed to illustrate the performance of the proposed method. We also applied the proposed method to concurrent EEG, EMG, and behavior data collected in a Parkinson's disease (PD) study. The results reveal highly correlated temporal patterns among the three types of signals and corresponding spatial activation patterns. In addition to the expected motor areas, the corresponding spatial activation patterns demonstrate enhanced occipital connectivity in the PD subjects, consistent with previous medical findings.

Details DOI

JMLR Journal 2009 Journal Article

Controlling the False Discovery Rate of the Association/Causality Structure Learned with the PC Algorithm

  • Junning Li
  • Z. Jane Wang

In real world applications, graphical statistical models are not only a tool for operations such as classification or prediction, but usually the network structures of the models themselves are also of great interest (e.g., in modeling brain connectivity). The false discovery rate (FDR), the expected ratio of falsely claimed connections to all those claimed, is often a reasonable error-rate criterion in these applications. However, current learning algorithms for graphical models have not been adequately adapted to the concerns of the FDR. The traditional practice of controlling the type I error rate and the type II error rate under a conventional level does not necessarily keep the FDR low, especially in the case of sparse networks. In this paper, we propose embedding an FDR-control procedure into the PC algorithm to curb the FDR of the skeleton of the learned graph. We prove that the proposed method can control the FDR under a user-specified level at the limit of large sample sizes. In the cases of moderate sample size (about several hundred), empirical experiments show that the method is still able to control the FDR under the user-specified level, and a heuristic modification of the method is able to control the FDR more accurately around the user-specified level. The proposed method is applicable to any models for which statistical tests of conditional independence are available, such as discrete models and Gaussian models. [abs] [ pdf ][ bib ] &copy JMLR 2009. ( edit, beta )

PDF Details