arXiv subjects

Yin Yang

Publications and source records attributed to Yin Yang.

At least 127 records · Page 7Linked to original sources

arXiv2023

An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation

Although existing deep learning compressed-sensing-based Magnetic Resonance Imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments. {In this work, to tackle explainability and generalizability, we propose a unifying deep unfolding multi-sampling-ratio interpretable CS-MRI framework.} The combined approach offers more generalizability than previous works whereas deep learning gains explainability through a geometric prior module. Inspired by the multigrid algorithm, we first embed the CS-MRI-based optimization algorithm into correction-distillation scheme that consists of three ingredients: pre-relaxation module, correction module and geometric prior distillation module. Furthermore, we employ a condition module to learn adaptively step-length and noise level, which enables the proposed framework to jointly train multi-ratio tasks through a single model. { The proposed model not only compensates for the lost contextual information of reconstructed image which is refined from low frequency error in geometric characteristic k-space}, but also integrates the theoretical guarantee of model-based methods and the superior reconstruction performances of deep learning-based methods. Therefore, it can give us a novel perspective to design biomedical imaging networks. { Numerical experiments show that our framework outperforms state-of-the-art methods in terms of qualitative and quantitative evaluations.} {Our method achieves 3.18 dB improvement at low CS ratio 10\% and average 1.42 dB improvement over other comparison methods on brain dataset using Cartesian sampling mask.

eess.IV↗

arXiv2023

AutoGMap: Learning to Map Large-scale Sparse Graphs on Memristive Crossbars

The sparse representation of graphs has shown great potential for accelerating the computation of graph applications (e.g., Social Networks, Knowledge Graphs) on traditional computing architectures (CPU, GPU, or TPU). But the exploration of large-scale sparse graph computing on processing-in-memory (PIM) platforms (typically with memristive crossbars) is still in its infancy. To implement the computation or storage of large-scale or batch graphs on memristive crossbars, a natural assumption is that a large-scale crossbar is demanded, but with low utilization. Some recent works question this assumption, to avoid the waste of storage and computational resource, the fixed-size or progressively scheduled ''block partition'' schemes are proposed. However, these methods are coarse-grained or static, and are not effectively sparsity-aware. This work proposes the dynamic sparsity-aware mapping scheme generating method that models the problem with a sequential decision-making model, and optimizes it by reinforcement learning (RL) algorithm (REINFORCE). Our generating model (LSTM, combined with the dynamic-fill scheme) generates remarkable mapping performance on a small-scale graph/matrix data (complete mapping costs 43% area of the original matrix) and two large-scale matrix data (costing 22.5% area on qh882 and 17.1% area on qh1484). Our method may be extended to sparse graph computing on other PIM architectures, not limited to the memristive device-based platforms.

cs.LG↗

arXiv2023

A Contact Proxy Splitting Method for Lagrangian Solid-Fluid Coupling

We present a robust and efficient method for simulating Lagrangian solid-fluid coupling based on a new operator splitting strategy. We use variational formulations to approximate fluid properties and solid-fluid interactions, and introduce a unified two-way coupling formulation for SPH fluids and FEM solids using interior point barrier-based frictional contact. We split the resulting optimization problem into a fluid phase and a solid-coupling phase using a novel time-splitting approach with augmented contact proxies, and propose efficient custom linear solvers. Our technique accounts for fluids interaction with nonlinear hyperelastic objects of different geometries and codimensions, while maintaining an algorithmically guaranteed non-penetrating criterion. Comprehensive benchmarks and experiments demonstrate the efficacy of our method.

cs.GR↗

arXiv2022

TPA-Net: Generate A Dataset for Text to Physics-based Animation

Recent breakthroughs in Vision-Language (V&L) joint research have achieved remarkable results in various text-driven tasks. High-quality Text-to-video (T2V), a task that has been long considered mission-impossible, was proven feasible with reasonably good results in latest works. However, the resulting videos often have undesired artifacts largely because the system is purely data-driven and agnostic to the physical laws. To tackle this issue and further push T2V towards high-level physical realism, we present an autonomous data generation technique and a dataset, which intend to narrow the gap with a large number of multi-modal, 3D Text-to-Video/Simulation (T2V/S) data. In the dataset, we provide high-resolution 3D physical simulations for both solids and fluids, along with textual descriptions of the physical phenomena. We take advantage of state-of-the-art physical simulation methods (i) Incremental Potential Contact (IPC) and (ii) Material Point Method (MPM) to simulate diverse scenarios, including elastic deformations, material fractures, collisions, turbulence, etc. Additionally, high-quality, multi-view rendering videos are supplied for the benefit of T2V, Neural Radiance Fields (NeRF), and other communities. This work is the first step towards fully automated Text-to-Video/Simulation (T2V/S). Live examples and subsequent work are at https://sites.google.com/view/tpa-net.

cs.AI↗

arXiv2022

Qubitization of Bosons

A binary mapping from Fock space of bosonic state to qubits is given. Based on the binary mapping, we construte an algorithm of qubitization of bosons with complexity O(log(N)). As an example, the algorithm of qubitization of bosons in matrix product state to simulate real time dynamics of Yukawa coupling is realized. The calculation error bar is estimated by random sampling method. This proposal may be achieved in superconductivity noisy intermediate--scale quantum computer not far future.

quant-ph↗

arXiv2022

Topology Optimization with Frictional Self-Contact

Contact-aware topology optimization faces challenges in robustness, accuracy, and applicability to internal structural surfaces under self-contact. This work builds on the recently proposed barrier-based Incremental Potential Contact (IPC) model and presents a new self-contact-aware topology optimization framework. A combination of SIMP, adjoint sensitivity analysis, and the IPC frictional-contact model is investigated. Numerical examples for optimizing varying objective functions under contact are presented. The resulting algorithm proposed solves topology optimization for large deformation and complex frictionally contacting scenarios with accuracy and robustness.

math.OC↗

arXiv2022

Automatic Quantization for Physics-Based Simulation

Quantization has proven effective in high-resolution and large-scale simulations, which benefit from bit-level memory saving. However, identifying a quantization scheme that meets the requirement of both precision and memory efficiency requires trial and error. In this paper, we propose a novel framework to allow users to obtain a quantization scheme by simply specifying either an error bound or a memory compression rate. Based on the error propagation theory, our method takes advantage of auto-diff to estimate the contributions of each quantization operation to the total error. We formulate the task as a constrained optimization problem, which can be efficiently solved with analytical formulas derived for the linearized objective function. Our workflow extends the Taichi compiler and introduces dithering to improve the precision of quantized simulations. We demonstrate the generality and efficiency of our method via several challenging examples of physics-based simulation, which achieves up to 2.5x memory compression without noticeable degradation of visual quality in the results. Our code and data are available at https://github.com/Hanke98/AutoQuantizer.

cs.GR↗

arXiv2022

Compatible $L^2$ norm convergence of variable-step L1 scheme for the time-fractional MBE mobel with slope selection

The convergence of variable-step L1 scheme is studied for the time-fractional molecular beam epitaxy (MBE) model with slope selection.A novel asymptotically compatible $L^2$ norm error estimate of the variable-step L1 scheme is established under a convergence-solvability-stability (CSS)-consistent time-step constraint. The CSS-consistent condition means that the maximum step-size limit required for convergence is of the same order to that for solvability and stability (in certain norms) as the small interface parameter $ε\rightarrow 0^+$. To the best of our knowledge, it is the first time to establish such error estimate for nonlinear subdiffusion problems. The asymptotically compatible convergence means that the error estimate is compatible with that of backward Euler scheme for the classical MBE model as the fractional order $α\rightarrow 1^-$. Just as the backward Euler scheme can maintain the physical properties of the MBE equation, the variable-step L1 scheme can also preserve the corresponding properties of the time-fractional MBE model, including the volume conservation, variational energy dissipation law and $L^2$ norm boundedness. Numerical experiments are presented to support our theoretical results.

math.NA↗

arXiv2022

Active Boundary Loss for Semantic Segmentation

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the movement of predicted boundaries in each iteration. Our loss is model-agnostic and can be plugged in to the training of segmentation networks to improve the boundary details. Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.

cs.CV↗

arXiv2022

Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction

Generating new images with desired properties (e.g. new view/poses) from source images has been enthusiastically pursued recently, due to its wide range of potential applications. One way to ensure high-quality generation is to use multiple sources with complementary information such as different views of the same object. However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques. Therefore, we propose a new general approach which models multiple types of variations among sources, such as view angles, poses, facial expressions, in a unified framework, so that it can be employed on datasets of vastly different nature. We verify our approach on a variety of data including humans bodies, faces, city scenes and 3D objects. Both the qualitative and quantitative results demonstrate the better performance of our method than the state of the art.

cs.CV↗

arXiv2022

Affine Body Dynamics: Fast, Stable & Intersection-free Simulation of Stiff Materials

Simulating stiff materials in applications where deformations are either not significant or can safely be ignored is a pivotal task across fields. Rigid body modeling has thus long remained a fundamental tool and is, by far, the most popular simulation strategy currently employed for modeling stiff solids. At the same time, numerical models of a rigid body continue to pose a number of known challenges and trade-offs including intersections, instabilities, inaccuracies, and/or slow performances that grow with contact-problem complexity. In this paper we revisit this problem and present ABD, a simple and highly effective affine body dynamics framework, which significantly improves state-of-the-art stiff simulations. We trace the challenges in the rigid-body IPC (incremental potential contact) method to the necessity of linearizing piecewise-rigid (SE(3)) trajectories and subsequent constraints. ABD instead relaxes the unnecessary (and unrealistic) constraint that each body's motion be exactly rigid with a stiff orthogonality potential, while preserving the rigid body model's key feature of a small coordinate representation. In doing so ABD replaces piecewise linearization with piecewise linear trajectories. This, in turn, combines the best from both parties: compact coordinates ensure small, sparse system solves, while piecewise-linear trajectories enable efficient and accurate constraint (contact and joint) evaluations. Beginning with this simple foundation, ABD preserves all guarantees of the underlying IPC model e.g., solution convergence, guaranteed non-intersection, and accurate frictional contact. Over a wide range and scale of simulation problems we demonstrate that ABD brings orders of magnitude performance gains (two- to three-order on the CPU and an order more utilizing the GPU, which is 10,000x speedups) over prior IPC-based methods with a similar or higher simulation quality.

cs.GR↗

arXiv2022

Online 3D Bin Packing with Constrained Deep Reinforcement Learning

We solve a challenging yet practically useful variant of 3D Bin Packing Problem (3D-BPP). In our problem, the agent has limited information about the items to be packed into the bin, and an item must be packed immediately after its arrival without buffering or readjusting. The item's placement also subjects to the constraints of collision avoidance and physical stability. We formulate this online 3D-BPP as a constrained Markov decision process. To solve the problem, we propose an effective and easy-to-implement constrained deep reinforcement learning (DRL) method under the actor-critic framework. In particular, we introduce a feasibility predictor to predict the feasibility mask for the placement actions and use it to modulate the action probabilities output by the actor during training. Such supervisions and transformations to DRL facilitate the agent to learn feasible policies efficiently. Our method can also be generalized e.g., with the ability to handle lookahead or items with different orientations. We have conducted extensive evaluation showing that the learned policy significantly outperforms the state-of-the-art methods. A user study suggests that our method attains a human-level performance.

cs.LG↗

arXiv2021

YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs

Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks, designed to complement our feature interaction module and together improve both accuracy as well as execution speed on various edge GPU devices available in the market. For instance, YOLO-ReT with MobileNetV2x0.75 backbone runs real-time on Jetson Nano, and achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO, beating its peers by 3.05 mAP and 0.91 mAP respectively, while executing faster by 3.05 FPS. Furthermore, introducing our multi-scale feature interaction module in YOLOv4-tiny and YOLOv4-tiny (3l) improves their performance to 41.5 and 48.1 mAP respectively on COCO, outperforming the original versions by 1.3 and 0.9 mAP.

cs.CV↗

arXiv2021

Effective and Scalable Clustering on Massive Attributed Graphs

Given a graph G where each node is associated with a set of attributes, and a parameter k specifying the number of output clusters, k-attributed graph clustering (k-AGC) groups nodes in G into k disjoint clusters, such that nodes within the same cluster share similar topological and attribute characteristics, while those in different clusters are dissimilar. This problem is challenging on massive graphs, e.g., with millions of nodes and billions of edges. For such graphs, existing solutions either incur prohibitively high costs, or produce clustering results with compromised quality. In this paper, we propose ACMin, an effective approach to k-AGC that yields high-quality clusters with cost linear to the size of the input graph G. The main contributions of ACMin are twofold: (i) a novel formulation of the k-AGC problem based on an attributed multi-hop conductance quality measure custom-made for this problem setting, which effectively captures cluster coherence in terms of both topological proximities and attribute similarities, and (ii) a linear-time optimization solver that obtains high-quality clusters iteratively, based on efficient matrix operations such as orthogonal iterations, an alternative optimization approach, as well as an initialization technique that significantly speeds up the convergence of ACMin in practice. Extensive experiments, comparing 11 competitors on 6 real datasets, demonstrate that ACMin consistently outperforms all competitors in terms of result quality measured against ground-truth labels, while being up to orders of magnitude faster. In particular, on the Microsoft Academic Knowledge Graph dataset with 265.2 million edges and 1.1 billion attribute values, ACMin outputs high-quality results for 5-AGC within 1.68 hours using a single CPU core, while none of the 11 competitors finish within 3 days.

cs.SI↗

arXiv2021

Deep Geometric Distillation Network for Compressive Sensing MRI

Compressed sensing (CS) is an efficient method to reconstruct MR image from small sampled data in $k$-space and accelerate the acquisition of MRI. In this work, we propose a novel deep geometric distillation network which combines the merits of model-based and deep learning-based CS-MRI methods, it can be theoretically guaranteed to improve geometric texture details of a linear reconstruction. Firstly, we unfold the model-based CS-MRI optimization problem into two sub-problems that consist of image linear approximation and image geometric compensation. Secondly, geometric compensation sub-problem for distilling lost texture details in approximation stage can be expanded by Taylor expansion to design a geometric distillation module fusing features of different geometric characteristic domains. Additionally, we use a learnable version with adaptive initialization of the step-length parameter, which allows model more flexibility that can lead to convergent smoothly. Numerical experiments verify its superiority over other state-of-the-art CS-MRI reconstruction approaches. The source code will be available at \url{https://github.com/fanxiaohong/Deep-Geometric-Distillation-Network-for-CS-MRI}

eess.IV↗

arXiv2021

Location-aware Single Image Reflection Removal

This paper proposes a novel location-aware deep-learning-based single image reflection removal method. Our network has a reflection detection module to regress a probabilistic reflection confidence map, taking multi-scale Laplacian features as inputs. This probabilistic map tells if a region is reflection-dominated or transmission-dominated, and it is used as a cue for the network to control the feature flow when predicting the reflection and transmission layers. We design our network as a recurrent network to progressively refine reflection removal results at each iteration. The novelty is that we leverage Laplacian kernel parameters to emphasize the boundaries of strong reflections. It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results. Extensive experiments verify the superior performance of the proposed method over state-of-the-art approaches. Our code and the pre-trained model can be found at https://github.com/zdlarr/Location-aware-SIRR.

cs.CV↗

arXiv2021

Unsupervised Image Generation with Infinite Generative Adversarial Networks

Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision. Generative Adversarial Networks (GANs) as an implicit approach have achieved great successes in this direction and therefore been employed widely. However, GANs are known to suffer from issues such as mode collapse, non-structured latent space, being unable to compute likelihoods, etc. In this paper, we propose a new unsupervised non-parametric method named mixture of infinite conditional GANs or MIC-GANs, to tackle several GAN issues together, aiming for image generation with parsimonious prior knowledge. Through comprehensive evaluations across different datasets, we show that MIC-GANs are effective in structuring the latent space and avoiding mode collapse, and outperform state-of-the-art methods. MICGANs are adaptive, versatile, and robust. They offer a promising solution to several well-known GAN issues. Code available: github.com/yinghdb/MICGANs.

cs.CV↗

arXiv2021

Training Massive Deep Neural Networks in a Smart Contract: A New Hope

Deep neural networks (DNNs) could be very useful in blockchain applications such as DeFi and NFT trading. However, training / running large-scale DNNs as part of a smart contract is infeasible on today's blockchain platforms, due to two fundamental design issues of these platforms. First, blockchains nowadays typically require that each node maintain the complete world state at any time, meaning that the node must execute all transactions in every block. This is prohibitively expensive for computationally intensive smart contracts involving DNNs. Second, existing blockchain platforms expect smart contract transactions to have deterministic, reproducible results and effects. In contrast, DNNs are usually trained / run lock-free on massively parallel computing devices such as GPUs, TPUs and / or computing clusters, which often do not yield deterministic results. This paper proposes novel platform designs, collectively called A New Hope (ANH), that address the above issues. The main ideas are (i) computing-intensive smart contract transactions are only executed by nodes who need their results, or by specialized serviced providers, and (ii) a non-deterministic smart contract transaction leads to uncertain results, which can still be validated, though at a relatively high cost; specifically for DNNs, the validation cost can often be reduced by verifying properties of the results instead of their exact values. In addition, we discuss various implications of ANH, including its effects on token fungibility, sharding, private transactions, and the fundamental meaning of a smart contract.

cs.CR↗