arXiv subjects

Bin Yan

Publications and source records attributed to Bin Yan.

At least 127 records · Page 7Linked to original sources

arXiv2020

AdvJND: Generating Adversarial Examples with Just Noticeable Difference

Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial examples. Adding small perturbations on examples causes a good-performance model to misclassify the crafted examples, without category differences in the human eyes, and fools deep models successfully. There are two requirements for generating adversarial examples: the attack success rate and image fidelity metrics. Generally, perturbations are increased to ensure the adversarial examples' high attack success rate; however, the adversarial examples obtained have poor concealment. To alleviate the tradeoff between the attack success rate and image fidelity, we propose a method named AdvJND, adding visual model coefficients, just noticeable difference coefficients, in the constraint of a distortion function when generating adversarial examples. In fact, the visual subjective feeling of the human eyes is added as a priori information, which decides the distribution of perturbations, to improve the image quality of adversarial examples. We tested our method on the FashionMNIST, CIFAR10, and MiniImageNet datasets. Adversarial examples generated by our AdvJND algorithm yield gradient distributions that are similar to those of the original inputs. Hence, the crafted noise can be hidden in the original inputs, thus improving the attack concealment significantly.

cs.CV↗

arXiv2020

Information Scrambling and Loschmidt Echo

We demonstrate analytically and verify numerically that the out-of-time order correlator is given by the thermal average of Loschmidt echo signals. This provides a direct link between the out-of-time-order correlator -- a recently suggested measure of information scrambling in quantum chaotic systems -- and the Loschmidt echo, a well-appreciated familiar diagnostic that captures the dynamical aspect of chaotic behavior in the time domain, and is accessible to experimental studies.

quant-ph↗

arXiv2020

Quantum Chaos on Complexity Geometry

This article tackles a fundamental long-standing problem in quantum chaos, namely, whether quantum chaotic systems can exhibit sensitivity to initial conditions, in a form that directly generalizes the notion of classical chaos in phase space. We develop a linear response theory for complexity, and demonstrate that the complexity can exhibit exponential sensitivity in response to perturbations of initial conditions for chaotic systems. Two immediate significant results follows: i) the complexity linear response matrix gives rise to a spectrum that fully recovers the Lyapunov exponents in the classical limit, and ii) the linear response of complexity is given by the out-of-time order correlators.

quant-ph↗

arXiv2020

Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features

On basis of functional magnetic resonance imaging (fMRI), researchers are devoted to designing visual encoding models to predict the neuron activity of human in response to presented image stimuli and analyze inner mechanism of human visual cortices. Deep network structure composed of hierarchical processing layers forms deep network models by learning features of data on specific task through big dataset. Deep network models have powerful and hierarchical representation of data, and have brought about breakthroughs for visual encoding, while revealing hierarchical structural similarity with the manner of information processing in human visual cortices. However, previous studies almost used image features of those deep network models pre-trained on classification task to construct visual encoding models. Except for deep network structure, the task or corresponding big dataset is also important for deep network models, but neglected by previous studies. Because image classification is a relatively fundamental task, it is difficult to guide deep network models to master high-level semantic representations of data, which causes into that encoding performance for high-level visual cortices is limited. In this study, we introduced one higher-level vision task: image caption (IC) task and proposed the visual encoding model based on IC features (ICFVEM) to encode voxels of high-level visual cortices. Experiment demonstrated that ICFVEM obtained better encoding performance than previous deep network models pre-trained on classification task. In addition, the interpretation of voxels was realized to explore the detailed characteristics of voxels based on the visualization of semantic words, and comparative analysis implied that high-level visual cortices behaved the correlative representation of image content.

cs.CV↗

arXiv2020

Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises

Adversarial attack of CNN aims at deceiving models to misbehave by adding imperceptible perturbations to images. This feature facilitates to understand neural networks deeply and to improve the robustness of deep learning models. Although several works have focused on attacking image classifiers and object detectors, an effective and efficient method for attacking single object trackers of any target in a model-free way remains lacking. In this paper, a cooling-shrinking attack method is proposed to deceive state-of-the-art SiameseRPN-based trackers. An effective and efficient perturbation generator is trained with a carefully designed adversarial loss, which can simultaneously cool hot regions where the target exists on the heatmaps and force the predicted bounding box to shrink, making the tracked target invisible to trackers. Numerous experiments on OTB100, VOT2018, and LaSOT datasets show that our method can effectively fool the state-of-the-art SiameseRPN++ tracker by adding small perturbations to the template or the search regions. Besides, our method has good transferability and is able to deceive other top-performance trackers such as DaSiamRPN, DaSiamRPN-UpdateNet, and DiMP. The source codes are available at https://github.com/MasterBin-IIAU/CSA.

cs.CV↗

arXiv2020

BigGAN-based Bayesian reconstruction of natural images from human brain activity

In the visual decoding domain, visually reconstructing presented images given the corresponding human brain activity monitored by functional magnetic resonance imaging (fMRI) is difficult, especially when reconstructing viewed natural images. Visual reconstruction is a conditional image generation on fMRI data and thus generative adversarial network (GAN) for natural image generation is recently introduced for this task. Although GAN-based methods have greatly improved, the fidelity and naturalness of reconstruction are still unsatisfactory due to the small number of fMRI data samples and the instability of GAN training. In this study, we proposed a new GAN-based Bayesian visual reconstruction method (GAN-BVRM) that includes a classifier to decode categories from fMRI data, a pre-trained conditional generator to generate natural images of specified categories, and a set of encoding models and evaluator to evaluate generated images. GAN-BVRM employs the pre-trained generator of the prevailing BigGAN to generate masses of natural images, and selects the images that best matches with the corresponding brain activity through the encoding models as the reconstruction of the image stimuli. In this process, the semantic and detailed contents of reconstruction are controlled by decoded categories and encoding models, respectively. GAN-BVRM used the Bayesian manner to avoid contradiction between naturalness and fidelity from current GAN-based methods and thus can improve the advantages of GAN. Experimental results revealed that GAN-BVRM improves the fidelity and naturalness, that is, the reconstruction is natural and similar to the presented image stimuli.

cs.CV↗

arXiv2020

Permutation Phase and Gentile Statistics

This paper presents a new way to construct single-valued many-body wavefunctions of identical particles with intermediate exchange phases between Fermi and Bose statistics. It is demonstrated that the exchange phase is not a representation character but the \textit{word metric} of the permutation group, beyond the anyon phase from the braiding group in two dimensions. By constructing this type of wavefunction from the direct product of single-particle states, it is shown that a finite \textit{capacity q} -- the maximally allowed particle occupation of each quantum state, naturally arises. The relation between the permutation phase and capacity is given, interpolating between fermions and bosons in the sense of both exchange phase and occupation number. This offers a quantum mechanics foundation for \textit{Gentile statistics} and new directions to explore intermediate statistics and anyons.

cond-mat.stat-mech↗

arXiv2019

CNN-based Automatic Detection of Bone Conditions via Diagnostic CT Images for Osteoporosis Screening

Purpose: The purpose is to design a novelty automatic diagnostic method for osteoporosis screening by using the potential capability of convolutional neural network (CNN) in feature representation and extraction, which can be incorporated into the procedure of routine CT diagnostic in physical examination thereby improving the osteoporosis diagnosis and reducing the patient burden. Methods: The proposed convolutional neural network-based method mainly comprises two functional modules to perform automatic detection of bone condition by analyzing the diagnostic CT image. The first functional module aims to locate and segment the ROI of diagnostic CT image, called Mark-Segmentation-Network (MS-Net). The second functional module is used to determine the category of bone condition by the features of ROI, called Bone-Conditions-Classification-Network (BCC-Net). The trained MS-Net can get the mark image of inputted original CT image, thereby obtain the segmentation image. The trained BCC-Net can obtain the probability value of normal bone mass, low bone mass, and osteoporosis by inputting the segmentation image. On the basis of network results, the radiologists can provide preliminary qualitative diagnosis results of bone condition. Results: The proposed MS-Net has an excellent segmentation precision on the shape preservation of different lumbar vertebra. The numerical indicators of segmentation results are greater than 0.998. The proposed BCC-Net was evaluated with 3,024 clinical images and achieved an accuracy of 76.65% and an area under the receiver operating characteristic curve of 0.9167. Conclusions: This study proposed a novel two-step method for automatic detection of bone conditions via diagnostic CT images and it has great potential in clinical applications for osteoporosis screening. The method can potentially reduce the manual burden to radiologists and diagnostic cost to patients.

physics.med-ph↗

arXiv2019

Resummation of High Order Corrections in $Z$ Boson Plus Jet Production at the LHC

We study the multiple soft gluon radiation effects in $Z$ boson plus jet production at the LHC. By applying the transverse momentum dependent factorization formalism, the large logarithms introduced by the small total transverse momentum of the $Z$ boson plus jet final state system, are resummed to all orders in the expansion of the strong interaction coupling at the accuracy of Next-to-Leading Logarithm(NLL). We also compare the prediction of our resummation calculation to the CMS data by employing a reweighting procedure to estimate the effect from imposing kinematic cuts on the leptons from $Z$ boson decay, and find good agreement for both the imbalance transverse momentum and the azimuthal angle correlation of the final state $Z$ boson and jet system, for $pp\to Z+jet$ production at the LHC.

hep-ph↗

arXiv2019

'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking

Compared with traditional short-term tracking, long-term tracking poses more challenges and is much closer to realistic applications. However, few works have been done and their performance have also been limited. In this work, we present a novel robust and real-time long-term tracking framework based on the proposed skimming and perusal modules. The perusal module consists of an effective bounding box regressor to generate a series of candidate proposals and a robust target verifier to infer the optimal candidate with its confidence score. Based on this score, our tracker determines whether the tracked object being present or absent, and then chooses the tracking strategies of local search or global search respectively in the next frame. To speed up the image-wide global search, a novel skimming module is designed to efficiently choose the most possible regions from a large number of sliding windows. Numerous experimental results on the VOT-2018 long-term and OxUvA long-term benchmarks demonstrate that the proposed method achieves the best performance and runs in real-time. The source codes are available at https://github.com/iiau-tracker/SPLT.

cs.CV↗

arXiv2019

Effective and efficient ROI-wise visual encoding using an end-to-end CNN regression model and selective optimization

Recently, visual encoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation. Visual encoding model is aimed at predicting brain activity in response to presented image stimuli. Currently, visual encoding is accomplished mainly by firstly extracting image features through convolutional neural network (CNN) model pre-trained on computer vision task, and secondly training a linear regression model to map specific layer of CNN features to each voxel, namely voxel-wise encoding. However, the two-step manner model, essentially, is hard to determine which kind of well features are well linearly matched for beforehand unknown fMRI data with little understanding of human visual representation. Analogizing computer vision mostly related human vision, we proposed the end-to-end convolution regression model (ETECRM) in the region of interest (ROI)-wise manner to accomplish effective and efficient visual encoding. The end-to-end manner was introduced to make the model automatically learn better matching features to improve encoding performance. The ROI-wise manner was used to improve the encoding efficiency for many voxels. In addition, we designed the selective optimization including self-adapting weight learning and weighted correlation loss, noise regularization to avoid interfering of ineffective voxels in ROI-wise encoding. Experiment demonstrated that the proposed model obtained better predicting accuracy than the two-step manner of encoding models. Comparative analysis implied that end-to-end manner and large volume of fMRI data may drive the future development of visual encoding.

q-bio.NC↗

arXiv2019

Resolving the degeneracy in top quark Yukawa coupling with Higgs pair production

The top quark Yukawa coupling ($y_t$) can be modified by two dimension-six operators $\mathcal{O}_H$ and $\mathcal{O}_y$ with the corresponding Wilson coefficients $c_H$ and $c_y$, whose individual contribution cannot be distinguished by measuring $y_t$ alone. However, such a degeneracy can be resolved with Higgs boson pair production. In this work we explore the potential of resolving the degeneracy of the unknown Wilson coefficients $c_H$ and $c_y$ at the 14~TeV LHC and the 100~TeV hadron colliders. Combining the information of the single Higgs production, $t\bar{t}h$ associated production and Higgs pair production, the individual contribution of $c_H$ and $c_y$ to $y_t$ can be separated. Regardless of the value of $c_H$, the Higgs pair production can give a strong constraint on $c_y$ at the 100 TeV hadron collider. We further show that it is possible to differentiate various $c_y$ and $c_t$ values predicted in several benchmark models.

hep-ph↗

arXiv2019

Cycle-Consistent Adversarial GAN: the integration of adversarial attack and defense

In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to them. Different attack and defense strategies have been proposed to better research the mechanism of deep learning. However, those research in these networks are only for one aspect, either an attack or a defense, not considering that attacks and defenses should be interdependent and mutually reinforcing, just like the relationship between spears and shields. In this paper, we propose Cycle-Consistent Adversarial GAN (CycleAdvGAN) to generate adversarial examples, which can learn and approximate the distribution of original instances and adversarial examples. For CycleAdvGAN, once the Generator and are trained, can generate adversarial perturbations efficiently for any instance, so as to make DNNs predict wrong, and recovery adversarial examples to clean instances, so as to make DNNs predict correct. We apply CycleAdvGAN under semi-white box and black-box settings on two public datasets MNIST and CIFAR10. Using the extensive experiments, we show that our method has achieved the state-of-the-art adversarial attack method and also efficiently improve the defense ability, which make the integration of adversarial attack and defense come true. In additional, it has improved attack effect only trained on the adversarial dataset generated by any kind of adversarial attack.

cs.CV↗

arXiv2019

Projection Super-resolution Based on Convolutional Neural Network for Computed Tomography

The improvement of computed tomography (CT) image resolution is beneficial to the subsequent medical diagnosis, but it is usually limited by the scanning devices and great expense. Convolutional neural network (CNN)-based methods have achieved promising ability in super-resolution. However, existing methods mainly focus on the super-resolution of reconstructed image and do not fully explored the approach of super-resolution from projection-domain. In this paper, we studied the characteristic of projection and proposed a CNN-based super-resolution method to establish the mapping relationship of low- and high-resolution projection. The network label is high-resolution projection and the input is its corresponding interpolation data after down sampling. FDK algorithm is utilized for three-dimensional image reconstruction and one slice of reconstruction image is taken as an example to evaluate the performance of the proposed method. Qualitative and quantitative results show that the proposed method is potential to improve the resolution of projection and enables the reconstructed image with higher quality.

physics.med-ph↗

arXiv2019

Category decoding of visual stimuli from human brain activity using a bidirectional recurrent neural network to simulate bidirectional information flows in human visual cortices

Recently, visual encoding and decoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation. Despite the hierarchically similar representations of deep network and human vision, visual information flows from primary visual cortices to high visual cortices and vice versa based on the bottom-up and top-down manners, respectively. Inspired by the bidirectional information flows, we proposed a bidirectional recurrent neural network (BRNN)-based method to decode the categories from fMRI data. The forward and backward directions in the BRNN module characterized the bottom-up and top-down manners, respectively. The proposed method regarded the selected voxels of each visual cortex region (V1, V2, V3, V4, and LO) as one node in the sequence fed into the BRNN module and combined the output of the BRNN module to decode the categories with the subsequent fully connected layer. This new method allows the efficient utilization of hierarchical information representations and bidirectional information flows in human visual cortices. Experiment results demonstrated that our method improved the accuracy of three-level category decoding than other methods, which implicitly validated the hierarchical and bidirectional human visual representations. Comparative analysis revealed that the category representations of human visual cortices were hierarchical, distributed, complementary, and correlative.

q-bio.NC↗

arXiv2019

A Sinogram Inpainting Method based on Generative Adversarial Network for Limited-angle Computed Tomography

Limited-angle computed tomography (CT) image reconstruction is a challenging reconstruction problem in the fields of CT. With the development of deep learning, the generative adversarial network (GAN) perform well in image restoration by approximating the distribution of training sample data. In this paper, we proposed an effective GAN-based inpainting method to restore the missing sinogram data for limited-angle scanning. To estimate the missing data, we design the generator and discriminator of the patch-GAN and train the network to learn the data distribution of the sinogram. We obtain the reconstructed image from the restored sinogram by filtered back projection and simultaneous algebraic reconstruction technique with total variation. Experimental results show that serious artifacts caused by missing projection data can be reduced by the proposed method, and it is hopeful to solve the reconstruction problem of 60 degrees limited scanning angle.

physics.med-ph↗

arXiv2019

A visual encoding model based on deep neural networks and transfer learning

Background: Building visual encoding models to accurately predict visual responses is a central challenge for current vision-based brain-machine interface techniques. To achieve high prediction accuracy on neural signals, visual encoding models should include precise visual features and appropriate prediction algorithms. Most existing visual encoding models employ hand-craft visual features (e.g., Gabor wavelets or semantic labels) or data-driven features (e.g., features extracted from deep neural networks (DNN)). They also assume a linear mapping between feature representation to brain activity. However, it remains unknown whether such linear mapping is sufficient for maximizing prediction accuracy. New Method: We construct a new visual encoding framework to predict cortical responses in a benchmark functional magnetic resonance imaging (fMRI) dataset. In this framework, we employ the transfer learning technique to incorporate a pre-trained DNN (i.e., AlexNet) and train a nonlinear mapping from visual features to brain activity. This nonlinear mapping replaces the conventional linear mapping and is supposed to improve prediction accuracy on brain activity. Results: The proposed framework can significantly predict responses of over 20% voxels in early visual areas (i.e., V1-lateral occipital region, LO) and achieve unprecedented prediction accuracy. Comparison with Existing Methods: Comparing to two conventional visual encoding models, we find that the proposed encoding model shows consistent higher prediction accuracy in all early visual areas, especially in relatively anterior visual areas (i.e., V4 and LO). Conclusions: Our work proposes a new framework to utilize pre-trained visual features and train non-linear mappings from visual features to brain activity.

cs.CV↗

arXiv2019

Soft Gluon Resummation in $t$-channel single top quark production at the LHC

We present a detailed phenomenological study of the multiple soft gluon radiation for the $t$-channel single top and anti-top quark production at the Large Hadron Collider (LHC). By applying the transverse momentum dependent factorization formalism, large logarithms introduced by small total transverse momentum $q_\perp$ of the single-top (anti-top) plus one-jet final state system are resummed to all orders in the expansion of the strong interaction coupling at the accuracy of Next-to-Leading Logarithm. We discuss various kinematical distributions which are sensitive to this effect and find that soft gluon radiation become more important when the final state jet is required to be in the forward region. We show that the main difference from PYTHIA prediction lies on the inclusion of the exact color coherence effect between the initial and final states in our resummation calculation. We further propose to apply the experimental observable $ϕ^*$ to test the effect of multiple gluon radiation in the single-top and anti-top events. The bottom quark mass effect and jet rapidity distribution are also discussed.

hep-ph↗