arXiv subjects

Yi Ma

Publications and source records attributed to Yi Ma.

At least 199 records · Page 11Linked to original sources

arXiv2022

Network-ELAA Beamforming and Coverage Analysis for eMBB/URLLC in Spatially Non-Stationary Rician Channels

In vehicle-to-infrastructure (V2I) networks, a cluster of multi-antenna access points (APs) can collaboratively conduct transmitter beamforming to provide data services (e.g., eMBB or URLLC). The collaboration between APs effectively forms a networked linear antenna-array with extra-large aperture (i.e., network-ELAA), where the wireless channel exhibits spatial nonstationarity. Major contribution of this work lies in the analysis of beamforming gain and radio coverage for network-ELAA non-stationary Rician channels considering the AP clustering. Assuming that: 1) the total transmit-power is fixed and evenly distributed over APs, 2) the beam is formed only based on the line-of-sight (LoS) path, it is found that the beamforming gain is concave to the cluster size. The optimum size of the AP cluster varies with respect to the user's location, channel uncertainty as well as data services. A user located farther from the ELAA requires a larger cluster size. URLLC is more sensitive to the channel uncertainty when comparing to eMBB, thus requiring a larger cluster size to mitigate the channel fading effect and extend the coverage. Finally, it is shown that the network-ELAA can offer significant coverage extension (50% or more in most of cases) when comparing with the single-AP scenario.

eess.SP↗

arXiv2022

DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

Scalable coding, which can adapt to channel bandwidth variation, performs well in today's complex network environment. However, the existing scalable compression methods face two challenges: reduced compression performance and insufficient scalability. In this paper, we propose the first learned fine-grained scalable image compression model (DeepFGS) to overcome the above two shortcomings. Specifically, we introduce a feature separation backbone to divide the image information into basic and scalable features, then redistribute the features channel by channel through an information rearrangement strategy. In this way, we can generate a continuously scalable bitstream via one-pass encoding. In addition, we reuse the decoder to reduce the parameters and computational complexity of DeepFGS. Experiments demonstrate that our DeepFGS outperforms all learning-based scalable image compression models and conventional scalable image codecs in PSNR and MS-SSIM metrics. To the best of our knowledge, our DeepFGS is the first exploration of learned fine-grained scalable coding, which achieves the finest scalability compared with learning-based methods.

eess.IV↗

arXiv2021

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction

This work attempts to provide a plausible theoretical framework that aims to interpret modern deep (convolutional) networks from the principles of data compression and discriminative representation. We argue that for high-dimensional multi-class data, the optimal linear discriminative representation maximizes the coding rate difference between the whole dataset and the average of all the subsets. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction objective naturally leads to a multi-layer deep network, named ReduNet, which shares common characteristics of modern deep networks. The deep layered architectures, linear and nonlinear operators, and even parameters of the network are all explicitly constructed layer-by-layer via forward propagation, although they are amenable to fine-tuning via back propagation. All components of so-obtained "white-box" network have precise optimization, statistical, and geometric interpretation. Moreover, all linear operators of the so-derived network naturally become multi-channel convolutions when we enforce classification to be rigorously shift-invariant. The derivation in the invariant setting suggests a trade-off between sparsity and invariance, and also indicates that such a deep convolution network is significantly more efficient to construct and learn in the spectral domain. Our preliminary simulations and experiments clearly verify the effectiveness of both the rate reduction objective and the associated ReduNet. All code and data are available at \url{https://github.com/Ma-Lab-Berkeley}.

cs.LG↗

arXiv2021

Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image

Single-image room layout reconstruction aims to reconstruct the enclosed 3D structure of a room from a single image. Most previous work relies on the cuboid-shape prior. This paper considers a more general indoor assumption, i.e., the room layout consists of a single ceiling, a single floor, and several vertical walls. To this end, we first employ Convolutional Neural Networks to detect planes and vertical lines between adjacent walls. Meanwhile, estimating the 3D parameters for each plane. Then, a simple yet effective geometric reasoning method is adopted to achieve room layout reconstruction. Furthermore, we optimize the 3D plane parameters to reconstruct a geometrically consistent room layout between planes and lines. The experimental results on public datasets validate the effectiveness and efficiency of our method.

cs.CV↗

arXiv2021

Massive-MIMO MF Beamforming with or without Grouped STBC for Ultra-Reliable Single-Shot Transmission Using Aged CSIT

The technology of using massive transmit-antennas to enable ultra-reliable single-shot transmission (URSST) is challenged by the transmitter-side channel knowledge (i.e., CSIT) imperfection. When the imperfectness mainly comes from the channel time-variation, the outage probability of the matched filter (MF) transmitter beamforming is investigated based on the first-order Markov model of the aged CSIT. With a fixed transmit-power, the transmitter-side uncertainty of the instantaneous signal-to-noise ratio (iSNR) is mathematically characterized. In order to guarantee the outage probability for every single shot, a transmit-power adaptation approach is proposed to satisfy a pessimistic iSNR requirement, which is predicted using the Chernoff lower bound of the beamforming gain. Our numerical results demonstrate a remarkable transmit-power efficiency when comparing with power control approaches using other lower bounds. In addition, a combinatorial approach of the MF beamforming and grouped space-time block code (G-STBC) is proposed to further mitigate the detrimental impact of the CSIT uncertainty. It is shown, through both theoretical analysis and computer simulations, that the combinatorial approach can further improve the transmit-power efficiency with a good tradeoff between the outage probability and the latency.

eess.SP↗

arXiv2021

PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance of speaker embedding extraction. To alleviate this problem, we propose an end-to-end deep learning framework, dubbed PL-EESR, for robust speaker representation extraction. This framework is optimized based on the feedback of the speaker identification task and the high-level perceptual deviation between the raw speech signal and its noisy version. We conducted speaker verification tasks in both noisy and clean environment respectively to evaluate our system. Compared to the baseline, our method shows better performance in both clean and noisy environments, which means our method can not only enhance the speaker relative information but also avoid adding distortions.

cs.SD↗

arXiv2021

Hermite Expansion Model and LMMSE Analysis for Low-Resolution Quantized MIMO Detection

In this paper, the Hermite polynomials are employed to study linear approximation models of narrowband multiantenna signal reception (i.e., MIMO) with low-resolution quantizations. This study results in a novel linear approximation using the second-order Hermite expansion (SOHE). The SOHE model is not based on those assumptions often used in existing linear approximations. Instead, the quantization distortion is characterized by the second-order Hermite kernel, and the signal term is characterized by the first-order Hermite kernel. It is shown that the SOHE model can explain almost all phenomena and characteristics observed so far in the low-resolution MIMO signal reception. When the SOHE model is employed to analyze the linear minimum-mean-square-error (LMMSE) channel equalizer, it is revealed that the current LMMSE algorithm can be enhanced by incorporating a symbol-level normalization mechanism. The performance of the enhanced LMMSE algorithm is demonstrated through computer simulations for narrowband MIMO systems in Rayleigh fading channels.

cs.IT↗

arXiv2021

Correlation-Based Device Energy-Efficient Dynamic Multi-Task Offloading for Mobile Edge Computing

Task offloading to mobile edge computing (MEC) has emerged as a key technology to alleviate the computation workloads of mobile devices and decrease service latency for the computation-intensive applications. Device battery consumption is one of the limiting factors needs to be considered during task offloading. In this paper, multi-task offloading strategies have been investigated to improve device energy efficiency. Correlations among tasks in time domain as well as task domain are proposed to be employed to reduce the number of tasks to be transmitted to MEC. Furthermore, a binary decision tree based algorithm is investigated to jointly optimize the mobile device clock frequency, transmission power, structure and number of tasks to be transmitted. MATLAB based simulation is employed to demonstrate the performance of our proposed algorithm. It is observed that the proposed dynamic multi-task offloading strategies can reduce the total energy consumption at device along various transmit power versus noise power point compared with the conventional one.

cs.NI↗

arXiv2021

A Non-Stationary Channel Model with Correlated NLoS/LoS States for ELAA-mMIMO

In this paper, a novel spatially non-stationary channel model is proposed for link-level computer simulations of massive multiple-input multiple-output (mMIMO) with extremely large aperture array (ELAA). The proposed channel model allows a mix of non-line-of-sight (NLoS) and LoS links between a user and service antennas. The NLoS/LoS state of each link is characterized by a binary random variable, which obeys a correlated Bernoulli distribution. The correlation is described in the form of an exponentially decaying window. In addition, the proposed model incorporates shadowing effects which are non-identical for NLoS and LoS states. It is demonstrated, through computer emulation, that the proposed model can capture almost all spatially non-stationary fading behaviors of the ELAA-mMIMO channel. Moreover, it has a low implementational complexity. With the proposed channel model, Monte-Carlo simulations are carried out to evaluate the channel capacity of ELAA-mMIMO. It is shown that the ELAA-mMIMO channel capacity has considerably different stochastic characteristics from the conventional mMIMO due to the presence of channel spatial non-stationarity.

cs.IT↗

arXiv2021

Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. In this paper, we study a fundamental problem in this context about recovering a surface mesh from an implicit field function whose zero-level set captures the underlying surface. To achieve the goal, existing methods rely on traditional meshing algorithms; while promising, they suffer from loss of precision learned in the implicit surface networks, due to the use of discrete space sampling in marching cubes. Given that an MLP with activations of Rectified Linear Unit (ReLU) partitions its input space into a number of linear regions, we are motivated to connect this local linearity with a same property owned by the desired result of polygon mesh. More specifically, we identify from the linear regions, partitioned by an MLP based implicit function, the analytic cells and analytic faces that are associated with the function's zero-level isosurface. We prove that under mild conditions, the identified analytic faces are guaranteed to connect and form a closed, piecewise planar surface. Based on the theorem, we propose an algorithm of analytic marching, which marches among analytic cells to exactly recover the mesh captured by an implicit surface network. We also show that our theory and algorithm are equally applicable to advanced MLPs with shortcut connections and max pooling. Given the parallel nature of analytic marching, we contribute AnalyticMesh, a software package that supports efficient meshing of implicit surface networks via CUDA parallel computing, and mesh simplification for efficient downstream processing. We apply our method to different settings of generative shape modeling using implicit surface networks. Extensive experiments demonstrate our advantages over existing methods in terms of both meshing accuracy and efficiency.

cs.CV↗

arXiv2021

Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition

Adversarially trained models exhibit a large generalization gap: they can interpolate the training set even for large perturbation radii, but at the cost of large test error on clean samples. To investigate this gap, we decompose the test risk into its bias and variance components and study their behavior as a function of adversarial training perturbation radii ($\varepsilon$). We find that the bias increases monotonically with $\varepsilon$ and is the dominant term in the risk. Meanwhile, the variance is unimodal as a function of $\varepsilon$, peaking near the interpolation threshold for the training set. This characteristic behavior occurs robustly across different datasets and also for other robust training procedures such as randomized smoothing. It thus provides a test for proposed explanations of the generalization gap. We find that some existing explanations fail this test--for instance, by predicting a monotonically increasing variance curve. This underscores the power of bias-variance decompositions in modern settings-by providing two measurements instead of one, they can rule out more explanations than test accuracy alone. We also show that bias and variance can provide useful guidance for scalably reducing the generalization gap, highlighting pre-training and unlabeled data as promising routes.

cs.LG↗

arXiv2021

Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients

In this paper we introduce a provably stable architecture for Neural Ordinary Differential Equations (ODEs) which achieves non-trivial adversarial robustness under white-box adversarial attacks even when the network is trained naturally. For most existing defense methods withstanding strong white-box attacks, to improve robustness of neural networks, they need to be trained adversarially, hence have to strike a trade-off between natural accuracy and adversarial robustness. Inspired by dynamical system theory, we design a stabilized neural ODE network named SONet whose ODE blocks are skew-symmetric and proved to be input-output stable. With natural training, SONet can achieve comparable robustness with the state-of-the-art adversarial defense methods, without sacrificing natural accuracy. Even replacing only the first layer of a ResNet by such a ODE block can exhibit further improvement in robustness, e.g., under PGD-20 ($\ell_\infty=0.031$) attack on CIFAR-10 dataset, it achieves 91.57\% and natural accuracy and 62.35\% robust accuracy, while a counterpart architecture of ResNet trained with TRADES achieves natural and robust accuracy 76.29\% and 45.24\%, respectively. To understand possible reasons behind this surprisingly good result, we further explore the possible mechanism underlying such an adversarial robustness. We show that the adaptive stepsize numerical ODE solver, DOPRI5, has a gradient masking effect that fails the PGD attacks which are sensitive to gradient information of training loss; on the other hand, it cannot fool the CW attack of robust gradients and the SPSA attack that is gradient-free. This provides a new explanation that the adversarial robustness of ODE-based networks mainly comes from the obfuscated gradients in numerical ODE solvers.

cs.LG↗

arXiv2021

End-to-End Wireframe Parsing

We present a conceptually simple yet effective algorithm to detect wireframes in a given image. Compared to the previous methods which first predict an intermediate heat map and then extract straight lines with heuristic algorithms, our method is end-to-end trainable and can directly output a vectorized wireframe that contains semantically meaningful and geometrically salient junctions and lines. To better understand the quality of the outputs, we propose a new metric for wireframe evaluation that penalizes overlapped line segments and incorrect line connectivities. We conduct extensive experiments and show that our method significantly outperforms the previous state-of-the-art wireframe and line extraction algorithms. We hope our simple approach can be served as a baseline for future wireframe parsing studies. Code has been made publicly available at https://github.com/zhou13/lcnn.

cs.CV↗

arXiv2021

End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels

In this paper, a novel end-to-end learning approach, namely JTRD-Net, is proposed for uplink multiuser single-input multiple-output (MU-SIMO) joint transmitter and non-coherent receiver design (JTRD) in fading channels. The basic idea lies in the use of artificial neural networks (ANNs) to replace traditional communication modules at both transmitter and receiver sides. More specifically, the transmitter side is modeled as a group of parallel linear layers, which are responsible for multiuser waveform design; and the non-coherent receiver is formed by a deep feed-forward neural network (DFNN) so as to provide multiuser detection (MUD) capabilities. The entire JTRD-Net can be trained from end to end to adapt to channel statistics through deep learning. After training, JTRD-Net can work efficiently in a non-coherent manner without requiring any levels of channel state information (CSI). In addition to the network architecture, a novel weight-initialization method, namely symmetrical-interval initialization, is proposed for JTRD-Net. It is shown that the symmetrical-interval initialization outperforms the conventional method (e.g. Xavier initialization) in terms of well-balanced convergence-rate among users. Simulation results show that the proposed JTRD-Net approach takes significant advantages in terms of reliability and scalability over baseline schemes on both i.i.d. complex Gaussian channels and spatially-correlated channels.

eess.SP↗

arXiv2021

NeRD: Neural 3D Reflection Symmetry Detector

Recent advances have shown that symmetry, a structural prior that most objects exhibit, can support a variety of single-view 3D understanding tasks. However, detecting 3D symmetry from an image remains a challenging task. Previous works either assume that the symmetry is given or detect the symmetry with a heuristic-based method. In this paper, we present NeRD, a Neural 3D Reflection Symmetry Detector, which combines the strength of learning-based recognition and geometry-based reconstruction to accurately recover the normal direction of objects' mirror planes. Specifically, we first enumerate the symmetry planes with a coarse-to-fine strategy and then find the best ones by building 3D cost volumes to examine the intra-image pixel correspondence from the symmetry. Our experiments show that the symmetry planes detected with our method are significantly more accurate than the planes from direct CNN regression on both synthetic and real-world datasets. We also demonstrate that the detected symmetry can be used to improve the performance of downstream tasks such as pose estimation and depth map regression. The code of this paper has been made public at https://github.com/zhou13/nerd.

cs.CV↗

arXiv2021

Learning to Reconstruct 3D Manhattan Wireframes from a Single Image

In this paper, we propose a method to obtain a compact and accurate 3D wireframe representation from a single image by effectively exploiting global structural regularities. Our method trains a convolutional neural network to simultaneously detect salient junctions and straight lines, as well as predict their 3D depth and vanishing points. Compared with the state-of-the-art learning-based wireframe detection methods, our network is simpler and more unified, leading to better 2D wireframe detection. With global structural priors from parallelism, our method further reconstructs a full 3D wireframe model, a compact vector representation suitable for a variety of high-level vision tasks such as AR and CAD. We conduct extensive evaluations on a large synthetic dataset of urban scenes as well as real images. Our code and datasets have been made public at https://github.com/zhou13/shapeunity.

cs.CV↗

arXiv2021

Complete Dictionary Learning via $\ell^4$-Norm Maximization over the Orthogonal Group

This paper considers the fundamental problem of learning a complete (orthogonal) dictionary from samples of sparsely generated signals. Most existing methods solve the dictionary (and sparse representations) based on heuristic algorithms, usually without theoretical guarantees for either optimality or complexity. The recent $\ell^1$-minimization based methods do provide such guarantees but the associated algorithms recover the dictionary one column at a time. In this work, we propose a new formulation that maximizes the $\ell^4$-norm over the orthogonal group, to learn the entire dictionary. We prove that under a random data model, with nearly minimum sample complexity, the global optima of the $\ell^4$ norm are very close to signed permutations of the ground truth. Inspired by this observation, we give a conceptually simple and yet effective algorithm based on "matching, stretching, and projection" (MSP). The algorithm provably converges locally at a superlinear (cubic) rate and cost per iteration is merely an SVD. In addition to strong theoretical guarantees, experiments show that the new algorithm is significantly more efficient and effective than existing methods, including KSVD and $\ell^1$-based methods. Preliminary experimental results on mixed real imagery data clearly demonstrate advantages of so learned dictionary over classic PCA bases.

cs.LG↗

arXiv2021

Learning Long-term Visual Dynamics with Region Proposal Interaction Networks

Learning long-term dynamics models is the key to understanding physical common sense. Most existing approaches on learning dynamics from visual input sidestep long-term predictions by resorting to rapid re-planning with short-term models. This not only requires such models to be super accurate but also limits them only to tasks where an agent can continuously obtain feedback and take action at each step until completion. In this paper, we aim to leverage the ideas from success stories in visual recognition tasks to build object representations that can capture inter-object and object-environment interactions over a long-range. To this end, we propose Region Proposal Interaction Networks (RPIN), which reason about each object's trajectory in a latent region-proposal feature space. Thanks to the simple yet effective object representation, our approach outperforms prior methods by a significant margin both in terms of prediction quality and their ability to plan for downstream tasks, and also generalize well to novel environments. Code, pre-trained models, and more visualization results are available at https://haozhi.io/RPIN.

cs.CV↗