arXiv subjects

Yipeng Liu

Publications and source records attributed to Yipeng Liu.

At least 73 records · Page 4Linked to original sources

arXiv2020

Hierarchical Tensor Ring Completion

Tensor completion can estimate missing values of a high-order data from its partially observed entries. Recent works show that low rank tensor ring approximation is one of the most powerful tools to solve tensor completion problem. However, existing algorithms need predefined tensor ring rank which may be hard to determine in practice. To address the issue, we propose a hierarchical tensor ring decomposition for more compact representation. We use the standard tensor ring to decompose a tensor into several 3-order sub-tensors in the first layer, and each sub-tensor is further factorized by tensor singular value decomposition (t-SVD) in the second layer. In the low rank tensor completion based on the proposed decomposition, the zero elements in the 3-order core tensor are pruned in the second layer, which helps to automatically determinate the tensor ring rank. To further enhance the recovery performance, we use total variation to exploit the locally piece-wise smoothness data structure. The alternating direction method of multiplier can divide the optimization model into several subproblems, and each one can be solved efficiently. Numerical experiments on color images and hyperspectral images demonstrate that the proposed algorithm outperforms state-of-the-arts ones in terms of recovery accuracy.

math.NA↗

arXiv2020

DaST: Data-free Substitute Training for Adversarial Attacks

Machine learning models are vulnerable to adversarial examples. For the black-box setting, current substitute attacks need pre-trained models to generate adversarial examples. However, pre-trained models are hard to obtain in real-world tasks. In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data. To achieve this, DaST utilizes specially designed generative adversarial networks (GANs) to train the substitute models. In particular, we design a multi-branch architecture and label-control loss for the generative model to deal with the uneven distribution of synthetic samples. The substitute model is then trained by the synthetic samples generated by the generative model, which are labeled by the attacked model subsequently. The experiments demonstrate the substitute models produced by DaST can achieve competitive performance compared with the baseline models which are trained by the same train set with attacked models. Additionally, to evaluate the practicability of the proposed method on the real-world task, we attack an online machine learning model on the Microsoft Azure platform. The remote model misclassifies 98.35% of the adversarial examples crafted by our method. To the best of our knowledge, we are the first to train a substitute model for adversarial attacks without any real data.

cs.CR↗

arXiv2020

Adversarial Imitation Attack

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate adversarial examples and their attack success rates heavily rely on the transferability of adversarial examples. Current score-based and decision-based attacks require lots of queries for the attacked models. In this study, we propose a novel adversarial imitation attack. First, it produces a replica of the attacked model by a two-player game like the generative adversarial networks (GANs). The objective of the generative model is to generate examples that lead the imitation model returning different outputs with the attacked model. The objective of the imitation model is to output the same labels with the attacked model under the same inputs. Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model. Compared with the current substitute attacks, imitation attacks can use less training data to produce a replica of the attacked model and improve the transferability of adversarial examples. Experiments demonstrate that our imitation attack requires less training data than the black-box substitute attacks, but achieves an attack success rate close to the white-box attack on unseen data with no query.

cs.CR↗

arXiv2020

Provable Tensor Ring Completion

Tensor completion recovers a multi-dimensional array from a limited number of measurements. Using the recently proposed tensor ring (TR) decomposition, in this paper we show that a d-order tensor of dimensional size n and TR rank r can be exactly recovered with high probability by solving a convex optimization program, given n^{d/2} r^2 ln^7(n^{d/2})samples. The proposed TR incoherence condition under which the result holds is similar to the matrix incoherence condition. The experiments on synthetic data verify the recovery guarantee for TR completion. Moreover, the experiments on real-world data show that our method improves the recovery performance compared with the state-of-the-art methods.

cs.LG↗

arXiv2018

Fast Signal Recovery from Saturated Measurements by Linear Loss and Nonconvex Penalties

Sign information is the key to overcoming the inevitable saturation error in compressive sensing systems, which causes information loss and results in bias. For sparse signal recovery from saturation, we propose to use a linear loss to improve the effectiveness from existing methods that utilize hard constraints/hinge loss for sign consistency. Due to the use of linear loss, an analytical solution in the update progress is obtained, and some nonconvex penalties are applicable, e.g., the minimax concave penalty, the $\ell_0$ norm, and the sorted $\ell_1$ norm. Theoretical analysis reveals that the estimation error can still be bounded. Generally, with linear loss and nonconvex penalties, the recovery performance is significantly improved, and the computational time is largely saved, which is verified by the numerical experiments.

cs.IT↗

arXiv2018

Image Ordinal Classification and Understanding: Grid Dropout with Masking Label

Image ordinal classification refers to predicting a discrete target value which carries ordering correlation among image categories. The limited size of labeled ordinal data renders modern deep learning approaches easy to overfit. To tackle this issue, neuron dropout and data augmentation were proposed which, however, still suffer from over-parameterization and breaking spatial structure, respectively. To address the issues, we first propose a grid dropout method that randomly dropout/blackout some areas of the raining image. Then we combine the objective of predicting the blackout patches with classification to take advantage of the spatial information. Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset. Experiments are conducted on a challenging age estimation dataset - Adience dataset with very competitive results compared with state-of-the-art methods.

cs.CV↗

arXiv2018

Low Rank Tensor Completion for Multiway Visual Data

Tensor completion recovers missing entries of multiway data. Teh missing of entries could often be caused during teh data acquisition and transformation. In dis paper, we provide an overview of recent development in low rank tensor completion for estimating teh missing components of visual data, e. g. , color images and videos. First, we categorize these methods into two groups based on teh different optimization models. One optimizes factors of tensor decompositions wif predefined tensor rank. Teh other iteratively updates teh estimated tensor via minimizing teh tensor rank. Besides, we summarize teh corresponding algorithms to solve those optimization problems in details. Numerical experiments are given to demonstrate teh performance comparison when different methods are applied to color image and video processing.

math.NA↗

arXiv2018

Mesh Interest Point Detection Based on Geometric Measures and Sparse Refinement

Three dimensional (3D) interest point detection plays a fundamental role in 3D computer vision and graphics. In this paper, we introduce a new method for detecting mesh interest points based on geometric measures and sparse refinement (GMSR). The key point of our approach is to calculate the 3D interest point response function using two intuitive and effective geometric properties of the local surface on a 3D mesh model, namely Euclidean distances between the neighborhood vertices to the tangent plane of a vertex and the angles of normal vectors of them. The response function is defined in multi-scale space and can be utilized to effectively distinguish 3D interest points from edges and flat areas. Those points with local maximal 3D interest point response value are selected as the candidates of 3D interest points. Finally, we utilize an $\ell_0$ norm based optimization method to refine the candidates of 3D interest points by constraining its quality and quantity. Numerical experiments demonstrate that our proposed GMSR based 3D interest point detector outperforms current several state-of-the-art methods for different kinds of 3D mesh models.

cs.CV↗

arXiv2017

Towards thinner convolutional neural networks through Gradually Global Pruning

Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices. Among many pruning granularities, neuron level pruning will remove redundant neurons and filters in the model and result in thinner networks. In this paper, we propose a gradually global pruning scheme for neuron level pruning. In each pruning step, a small percent of neurons were selected and dropped across all layers in the model. We also propose a simple method to eliminate the biases in evaluating the importance of neurons to make the scheme feasible. Compared with layer-wise pruning scheme, our scheme avoid the difficulty in determining the redundancy in each layer and is more effective for deep networks. Our scheme would automatically find a thinner sub-network in original network under a given performance.

cs.CV↗

arXiv2017

Attribute-controlled face photo synthesis from simple line drawing

Face photo synthesis from simple line drawing is a one-to-many task as simple line drawing merely contains the contour of human face. Previous exemplar-based methods are over-dependent on the datasets and are hard to generalize to complicated natural scenes. Recently, several works utilize deep neural networks to increase the generalization, but they are still limited in the controllability of the users. In this paper, we propose a deep generative model to synthesize face photo from simple line drawing controlled by face attributes such as hair color and complexion. In order to maximize the controllability of face attributes, an attribute-disentangled variational auto-encoder (AD-VAE) is firstly introduced to learn latent representations disentangled with respect to specified attributes. Then we conduct photo synthesis from simple line drawing based on AD-VAE. Experiments show that our model can well disentangle the variations of attributes from other variations of face photos and synthesize detailed photorealistic face images with desired attributes. Regarding background and illumination as the style and human face as the content, we can also synthesize face photos with the target style of a style photo.

cs.CV↗

arXiv2017

Iterative Block Tensor Singular Value Thresholding for Extraction of Low Rank Component of Image Data

Tensor principal component analysis (TPCA) is a multi-linear extension of principal component analysis which converts a set of correlated measurements into several principal components. In this paper, we propose a new robust TPCA method to extract the princi- pal components of the multi-way data based on tensor singular value decomposition. The tensor is split into a number of blocks of the same size. The low rank component of each block tensor is extracted using iterative tensor singular value thresholding method. The prin- cipal components of the multi-way data are the concatenation of all the low rank components of all the block tensors. We give the block tensor incoherence conditions to guarantee the successful decom- position. This factorization has similar optimality properties to that of low rank matrix derived from singular value decomposition. Ex- perimentally, we demonstrate its effectiveness in two applications, including motion separation for surveillance videos and illumination normalization for face images.

cs.CV↗

arXiv2016

Every Filter Extracts A Specific Texture In Convolutional Neural Networks

Many works have concentrated on visualizing and understanding the inner mechanism of convolutional neural networks (CNNs) by generating images that activate some specific neurons, which is called deep visualization. However, it is still unclear what the filters extract from images intuitively. In this paper, we propose a modified code inversion algorithm, called feature map inversion, to understand the function of filter of interest in CNNs. We reveal that every filter extracts a specific texture. The texture from higher layer contains more colours and more intricate structures. We also demonstrate that style of images could be a combination of these texture primitives. Two methods are proposed to reallocate energy distribution of feature maps randomly and purposefully. Then, we inverse the modified code and generate images of diverse styles. With these results, we provide an explanation about why Gram matrix of feature maps \cite{Gatys_2016_CVPR} could represent image style.

cs.CV↗

arXiv2016

3D Keypoint Detection Based on Deep Neural Network with Sparse Autoencoder

Researchers have proposed various methods to extract 3D keypoints from the surface of 3D mesh models over the last decades, but most of them are based on geometric methods, which lack enough flexibility to meet the requirements for various applications. In this paper, we propose a new method on the basis of deep learning by formulating the 3D keypoint detection as a regression problem using deep neural network (DNN) with sparse autoencoder (SAE) as our regression model. Both local information and global information of a 3D mesh model in multi-scale space are fully utilized to detect whether a vertex is a keypoint or not. SAE can effectively extract the internal structure of these two kinds of information and formulate high-level features for them, which is beneficial to the regression model. Three SAEs are used to formulate the hidden layers of the DNN and then a logistic regression layer is trained to process the high-level features produced in the third SAE. Numerical experiments show that the proposed DNN based 3D keypoint detection algorithm outperforms current five state-of-the-art methods for various 3D mesh models.

cs.CV↗

arXiv2016

Efficient $\ell_q$ Minimization Algorithms for Compressive Sensing Based on Proximity Operator

This paper considers solving the unconstrained $\ell_q$-norm ($0\leq q<1$) regularized least squares ($\ell_q$-LS) problem for recovering sparse signals in compressive sensing. We propose two highly efficient first-order algorithms via incorporating the proximity operator for nonconvex $\ell_q$-norm functions into the fast iterative shrinkage/thresholding (FISTA) and the alternative direction method of multipliers (ADMM) frameworks, respectively. Furthermore, in solving the nonconvex $\ell_q$-LS problem, a sequential minimization strategy is adopted in the new algorithms to gain better global convergence performance. Unlike most existing $\ell_q$-minimization algorithms, the new algorithms solve the $\ell_q$-minimization problem without smoothing (approximating) the $\ell_q$-norm. Meanwhile, the new algorithms scale well for large-scale problems, as often encountered in image processing. We show that the proposed algorithms are the fastest methods in solving the nonconvex $\ell_q$-minimization problem, while offering competent performance in recovering sparse signals and compressible images compared with several state-of-the-art algorithms.

cs.IT↗

arXiv2015

Robust Compressed Sensing Under Matrix Uncertainties

Compressed sensing (CS) shows that a signal having a sparse or compressible representation can be recovered from a small set of linear measurements. In classical CS theory, the sampling matrix and representation matrix are assumed to be known exactly in advance. However, uncertainties exist due to sampling distortion, finite grids of the parameter space of dictionary, etc. In this paper, we take a generalized sparse signal model, which simultaneously considers the sampling and representation matrix uncertainties. Based on the new signal model, a new optimization model for robust sparse signal reconstruction is proposed. This optimization model can be deduced with stochastic robust approximation analysis. Both convex relaxation and greedy algorithms are used to solve the optimization problem. For the convex relaxation method, a sufficient condition for recovery by convex relaxation is given; For the greedy algorithm, it is realized by the introduction of a pre-processing of the sensing matrix and the measurements. In numerical experiments, both simulated data and real-life ECG data based results show that the proposed method has a better performance than the current methods.

cs.IT↗

arXiv2015

Compressed Sensing of Multi-Channel EEG Signals: The Simultaneous Cosparsity and Low Rank Optimization

Goal: This paper deals with the problems that some EEG signals have no good sparse representation and single channel processing is not computationally efficient in compressed sensing of multi-channel EEG signals. Methods: An optimization model with L0 norm and Schatten-0 norm is proposed to enforce cosparsity and low rank structures in the reconstructed multi-channel EEG signals. Both convex relaxation and global consensus optimization with alternating direction method of multipliers are used to compute the optimization model. Results: The performance of multi-channel EEG signal reconstruction is improved in term of both accuracy and computational complexity. Conclusion: The proposed method is a better candidate than previous sparse signal recovery methods for compressed sensing of EEG signals. Significance: The proposed method enables successful compressed sensing of EEG signals even when the signals have no good sparse representation. Using compressed sensing would much reduce the power consumption of wireless EEG system.

cs.IT↗

arXiv2014

Robust Cosparse Greedy Signal Reconstruction for Compressive Sensing with Multiplicative and Additive Noise

Greedy algorithms are popular in compressive sensing for their high computational efficiency. But the performance of current greedy algorithms can be degenerated seriously by noise (both multiplicative noise and additive noise). A robust version of greedy cosparse greedy algorithm (greedy analysis pursuit) is presented in this paper. Comparing with previous methods, The proposed robust greedy analysis pursuit algorithm is based on an optimization model which allows both multiplicative noise and additive noise in the data fitting constraint. Besides, a new stopping criterion that is derived. The new algorithm is applied to compressive sensing of ECG signals. Numerical experiments based on real-life ECG signals demonstrate the performance improvement of the proposed greedy algorithms.

cs.IT↗

arXiv2013

Simultaneous Greedy Analysis Pursuit for Compressive Sensing of Multi-Channel ECG Signals

This paper addresses compressive sensing for multi-channel ECG. Compared to the traditional sparse signal recovery approach which decomposes the signal into the product of a dictionary and a sparse vector, the recently developed cosparse approach exploits sparsity of the product of an analysis matrix and the original signal. We apply the cosparse Greedy Analysis Pursuit (GAP) algorithm for compressive sensing of ECG signals. Moreover, to reduce processing time, classical signal-channel GAP is generalized to the multi-channel GAP algorithm, which simultaneously reconstructs multiple signals with similar support. Numerical experiments show that the proposed method outperforms the classical sparse multi-channel greedy algorithms in terms of accuracy and the single-channel cosparse approach in terms of processing speed.

cs.IT↗