arXiv subjects

Ming Zhao

Publications and source records attributed to Ming Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2023

Design of a vector multi-foci metalens for full stokes imaging polarimetry

Imaging polarimetry based on dielectric metasurface is well-known for its ultra-compactness and high integration. However, previous works suffer from low energy efficiency, limited restrictions on choice of target polarization states, or inability to focus light. Here, by inverse design, we numerically demonstrate a multi-foci metalens-based polarimetry that can simultaneously separate and focus the four free-chosen elliptical polarization states at the wavelength of 10.6 μm. Such a full-stokes polarimetry features an average absolute efficiency up to 54.63%, and an average relative error as low as 0.00137%. This spatial-multiplexing-free full stokes polarimetry exceeds the theoretical maximum efficiency of traditional polarization-filtering counterparts, and resolves the restriction faced by the orthogonal polarization-multiplexed method.

physics.optics↗

arXiv2023

AdaCache: A Disaggregated Cache System with Adaptive Block Size for Cloud Block Storage

NVMe SSD caching has demonstrated impressive capabilities in solving cloud block storage's I/O bottleneck and enhancing application performance in public, private, and hybrid cloud environments. However, traditional host-side caching solutions have several serious limitations. First, the cache cannot be shared across hosts, leading to low cache utilization. Second, the commonly-used fix-sized cache block allocation mechanism is unable to provide good cache performance with low memory overhead for diverse cloud workloads with vastly different I/O patterns. This paper presents AdaCache, a novel userspace disaggregated cache system that utilizes adaptive cache block allocation for cloud block storage. First, AdaCache proposes an innovative adaptive cache block allocation scheme that allocates cache blocks based on the request size to achieve both good cache performance and low memory overhead. Second, AdaCache proposes a group-based cache organization that stores cache blocks into groups to solve the fragmentation problem brought by variable-sized cache blocks. Third, AdaCache designs a two-level cache replacement policy that replaces cache blocks in both single blocks and groups to improve the hit ratio. Experimental results with real-world traces show that AdaCache can substantially improve I/O performance and reduce storage access caused by cache miss with a much lower memory usage compared to traditional fix-sized cache systems.

cs.DC↗

arXiv2023

When Edge Meets FaaS: Opportunities and Challenges

The proliferation of edge devices and the rapid growth of IoT data have called forth the edge computing paradigm. Function-as-a-service (FaaS) is a promising computing paradigm to realize edge computing. This paper explores the feasibility and advantages of FaaS-based edge computing. It also studies the research challenges that should be addressed in the design of such systems, which are 1) the quick decomposing and recomposing of applications, 2) the trade-off between performance and isolation of sandbox mechanisms, and 3) distributed scheduling. The challenges are illustrated by evaluating existing FaaS-based edge platforms, AWS IoT Greengrass, and OpenFaaS.

cs.DC↗

arXiv2023

Confidence-based federated distillation for vision-based lane-centering

A fundamental challenge of autonomous driving is maintaining the vehicle in the center of the lane by adjusting the steering angle. Recent advances leverage deep neural networks to predict steering decisions directly from images captured by the car cameras. Machine learning-based steering angle prediction needs to consider the vehicle's limitation in uploading large amounts of potentially private data for model training. Federated learning can address these constraints by enabling multiple vehicles to collaboratively train a global model without sharing their private data, but it is difficult to achieve good accuracy as the data distribution is often non-i.i.d. across the vehicles. This paper presents a new confidence-based federated distillation method to improve the performance of federated learning for steering angle prediction. Specifically, it proposes the novel use of entropy to determine the predictive confidence of each local model, and then selects the most confident local model as the teacher to guide the learning of the global model. A comprehensive evaluation of vision-based lane centering shows that the proposed approach can outperform FedAvg and FedDF by 11.3% and 9%, respectively.

cs.CV↗

arXiv2023

Exploring the non-stationarity of coastal sea level probability distributions

Studies agree on a significant global mean sea level rise in the 20th century and its recent 21st century acceleration in the satellite record. At regional scale, the evolution of sea level probability distributions is often assumed to be dominated by changes in the mean. However, a quantification of changes in distributional shapes in a changing climate is currently missing. To this end, we propose a novel framework quantifying significant changes in probability distributions from time series data. The framework first quantifies linear trends in quantiles through quantile regression. Quantile slopes are then projected onto a set of four $orthogonal$ polynomials quantifying how such changes can be explained by $independent$ shifts in the first four statistical moments. The framework proposed is theoretically founded, general and can be applied to any climate observable with close-to-linear changes in distributions. We focus on observations and a coupled climate model (GFDL-CM4). In the historical period, trends in coastal daily sea level have been driven mainly by changes in the mean and can therefore be explained by a shift of the distribution with no change in shape. In the modeled world, robust changes in higher order moments emerge with increasing CO2 concentration. Such changes are driven in part by ocean circulation alone and get amplified by sea level pressure fluctuations, with possible consequences for sea level extremes attribution studies.

physics.ao-ph↗

arXiv2023

A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning

Knowledge Transfer (KT) achieves competitive performance and is widely used for image classification tasks in model compression and transfer learning. Existing KT works transfer the information from a large model ("teacher") to train a small model ("student") by minimizing the difference of their conditionally independent output distributions. However, these works overlook the high-dimension structural knowledge from the intermediate representations of the teacher, which leads to limited effectiveness, and they are motivated by various heuristic intuitions, which makes it difficult to generalize. This paper proposes a novel Contrastive Knowledge Transfer Framework (CKTF), which enables the transfer of sufficient structural knowledge from the teacher to the student by optimizing multiple contrastive objectives across the intermediate representations between them. Also, CKTF provides a generalized agreement to existing KT techniques and increases their performance significantly by deriving them as specific cases of CKTF. The extensive evaluation shows that CKTF consistently outperforms the existing KT works by 0.04% to 11.59% in model compression and by 0.4% to 4.75% in transfer learning on various models and datasets.

cs.LG↗

arXiv2023

Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions

Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot efficiently run on commodity hardware; and they often require users to manually explore and tune the pruning process, which is time-consuming and often leads to sub-optimal results. To address these limitations, this paper presents Automatic Attention Pruning (AAP), an adaptive, attention-based, structured pruning approach to automatically generate small, accurate, and hardware-efficient models that meet user objectives. First, it proposes iterative structured pruning using activation-based attention maps to effectively identify and prune unimportant filters. Then, it proposes adaptive pruning policies for automatically meeting the pruning objectives of accuracy-critical, memory-constrained, and latency-sensitive tasks. A comprehensive evaluation shows that AAP substantially outperforms the state-of-the-art structured pruning works for a variety of model architectures. Our code is at: https://github.com/kaiqi123/Automatic-Attention-Pruning.git.

cs.LG↗

arXiv2023

Adaptive Activation-based Structured Pruning

Pruning is a promising approach to compress complex deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot efficiently run on commodity hardware and require users to manually explore and tune the pruning process, which is time-consuming and often leads to sub-optimal results. To address these limitations, this paper presents an adaptive, activation-based, structured pruning approach to automatically and efficiently generate small, accurate, and hardware-efficient models that meet user requirements. First, it proposes iterative structured pruning using activation-based attention feature maps to effectively identify and prune unimportant filters. Then, it proposes adaptive pruning policies for automatically meeting the pruning objectives of accuracy-critical, memory-constrained, and latency-sensitive tasks. A comprehensive evaluation shows that the proposed method can substantially outperform the state-of-the-art structured pruning works on CIFAR-10 and ImageNet datasets. For example, on ResNet-56 with CIFAR-10, without any accuracy drop, our method achieves the largest parameter reduction (79.11%), outperforming the related works by 22.81% to 66.07%, and the largest FLOPs reduction (70.13%), outperforming the related works by 14.13% to 26.53%.

cs.CV↗

arXiv2023

GPU-enabled Function-as-a-Service for Machine Learning Inference

Function-as-a-Service (FaaS) is emerging as an important cloud computing service model as it can improve the scalability and usability of a wide range of applications, especially Machine-Learning (ML) inference tasks that require scalable resources and complex software configurations. These inference tasks heavily rely on GPUs to achieve high performance; however, support for GPUs is currently lacking in the existing FaaS solutions. The unique event-triggered and short-lived nature of functions poses new challenges to enabling GPUs on FaaS, which must consider the overhead of transferring data (e.g., ML model parameters and inputs/outputs) between GPU and host memory. This paper proposes a novel GPU-enabled FaaS solution that enables ML inference functions to efficiently utilize GPUs to accelerate their computations. First, it extends existing FaaS frameworks such as OpenFaaS to support the scheduling and execution of functions across GPUs in a FaaS cluster. Second, it provides caching of ML models in GPU memory to improve the performance of model inference functions and global management of GPU memories to improve cache utilization. Third, it offers co-designed GPU function scheduling and cache management to optimize the performance of ML inference functions. Specifically, the paper proposes locality-aware scheduling, which maximizes the utilization of both GPU memory for cache hits and GPU cores for parallel processing. A thorough evaluation based on real-world traces and ML models shows that the proposed GPU-enabled FaaS works well for ML inference tasks, and the proposed locality-aware scheduler achieves a speedup of 48x compared to the default, load balancing only schedulers.

cs.DC↗

arXiv2022

Quench dynamics in the one-dimensional mass-imbalanced ionic Hubbard model

Using the time-dependent Lanczos method, we study the non-equilibrium dynamics of the one-dimensional ionic-mass imbalanced Hubbard chain driven by a quantum quench of the on-site Coulomb interaction, where the system is prepared in the ground state of the Hamiltonian with a different Hubbard interaction. A full exact diagonalization is adopted to study the zero temperature phase diagram in equilibrium, which is shown to be in good agreement with previous studies using density matrix renormalization group (DMRG). We then study the non-equilibrium quench dynamics of the spin and charge order parameters by fixing the initial and final Coulomb interaction while changing the quenching time protocols. The Lanczos method allows us to reach longer times following the quench than DMRG. Our study shows that the time evolution of the charge and spin order parameters strongly depend on the quenching time protocols. In particular, the effective temperature of the system will decrease monotonically as the quenching time is increased. Finally, by taking the final Coulomb interaction strength to be in the strong coupling regime, we find that the oscillation frequency of the charge order parameter increases monotonically with the Coulomb interaction. By contrast, the frequency of the spin order parameter decreases monotonically with increasing Coulomb interaction. We explain this result using an effective spin model in the strong coupling limit. Our study suggests strategies to engineer the relaxation behavior of interacting quantum many-particle systems.

cond-mat.str-el↗

arXiv2022

Design of an achromatic zoom metalens doublet in the visible

Zoom metalens doublet exhibits unprecedented advantages over the traditional zoom lens in many aspects, like ultra-compactness, CMOS compatibility, and miniaturization. However, most of them can only work in a narrow band due to chromatic aberration. Here, we numerically demonstrate a broadband achromatic zoom metalens doublet inspired by the Moiré lens principle. This design is achieved by globally optimizing the multi-wavelength phase profiles of the metalens doublet in the visible. The doublet can achieve achromatic continuous 1-10 zoom range at wavelengths of 440 nm, 540 nm, and 640 nm, featuring high focusing efficiency up to 86.5% and polarization insensitivity.

physics.optics↗

arXiv2022

A centimeter-scale achromatic hybrid metalens with polarization-insensitivity in the visible

Metalenses, featuring ultra-compactness and CMOS compatibility, are limited by the compromise between the diameter, numerical aperture, and working waveband. To address this problem, we propose and numerically demonstrate a centimeter-scale metasurface-refractive hybrid metalens working in the band of 440 - 700 nm. Revisiting the general Snell law, we present the phase profile of a chromatic aberration correction metasurface that can apply to a plano-convex refractive lens of an arbitrary surface type. Simulated by our semi-vector method, the designed achromatic hybrid metalens achieves 81% chromatic aberration suppression and polarization insensitivity. Broadband imaging results of the hybrid metalens are further provided, verifying the achromatism of the designed hybrid metalens. It can find applications in camera lenses and other optical systems that need compact, high-performance lenses.

physics.optics↗

arXiv2022

Serving Deep Learning Models with Deduplication from Relational Databases

There are significant benefits to serve deep learning models from relational databases. First, features extracted from databases do not need to be transferred to any decoupled deep learning systems for inferences, and thus the system management overhead can be significantly reduced. Second, in a relational database, data management along the storage hierarchy is fully integrated with query processing, and thus it can continue model serving even if the working set size exceeds the available memory. Applying model deduplication can greatly reduce the storage space, memory footprint, cache misses, and inference latency. However, existing data deduplication techniques are not applicable to the deep learning model serving applications in relational databases. They do not consider the impacts on model inference accuracy as well as the inconsistency between tensor blocks and database pages. This work proposed synergistic storage optimization techniques for duplication detection, page packing, and caching, to enhance database systems for model serving. We implemented the proposed approach in netsDB, an object-oriented relational database. Evaluation results show that our proposed techniques significantly improved the storage efficiency and the model inference latency, and serving models from relational databases outperformed existing deep learning frameworks when the working set size exceeds available memory.

cs.DB↗

arXiv2022

Leveraging Reaction-aware Substructures for Retrosynthesis Analysis

Retrosynthesis analysis is a critical task in organic chemistry central to many important industries. Previously, various machine learning approaches have achieved promising results on this task by representing output molecules as strings and autoregressively decoded token-by-token with generative models. Text generation or machine translation models in natural language processing were frequently utilized approaches. The token-by-token decoding approach is not intuitive from a chemistry perspective because some substructures are relatively stable and remain unchanged during reactions. In this paper, we propose a substructure-level decoding model, where the substructures are reaction-aware and can be automatically extracted with a fully data-driven approach. Our approach achieved improvement over previously reported models, and we find that the performance can be further boosted if the accuracy of substructure extraction is improved. The substructures extracted by our approach can provide users with better insights for decision-making compared to existing methods. We hope this work will generate interest in this fast growing and highly interdisciplinary area on retrosynthesis prediction and other related topics.

q-bio.QM↗

arXiv2022

RGB-X Classification for Electronics Sorting

Effectively disassembling and recovering materials from waste electrical and electronic equipment (WEEE) is a critical step in moving global supply chains from carbon-intensive, mined materials to recycled and renewable ones. Conventional recycling processes rely on shredding and sorting waste streams, but for WEEE, which is comprised of numerous dissimilar materials, we explore targeted disassembly of numerous objects for improved material recovery. Many WEEE objects share many key features and therefore can look quite similar, but their material composition and internal component layout can vary, and thus it is critical to have an accurate classifier for subsequent disassembly steps for accurate material separation and recovery. This work introduces RGB-X, a multi-modal image classification approach, that utilizes key features from external RGB images with those generated from X-ray images to accurately classify electronic objects. More specifically, this work develops Iterative Class Activation Mapping (iCAM), a novel network architecture that explicitly focuses on the finer-details in the multi-modal feature maps that are needed for accurate electronic object classification. In order to train a classifier, electronic objects lack large and well annotated X-ray datasets due to expense and need of expert guidance. To overcome this issue, we present a novel way of creating a synthetic dataset using domain randomization applied to the X-ray domain. The combined RGB-X approach gives us an accuracy of 98.6% on 10 generations of modern smartphones, which is greater than their individual accuracies of 89.1% (RGB) and 97.9% (X-ray) independently. We provide experimental results3 to corroborate our results.

cs.CV↗

arXiv2022

Phase-Only Holographic Assisted Planar Printing for Massively Multiplexed Optical Display and Encryption

Multiplexed planar printings, made of single or few layer micro and nano optical platforms, are essential for high capacity display, information storage and encryption. Although having been developed rapidly, the demonstrated channels are still limited and also lack instantaneity. Here, holograms and printings, always regarded as two independent information coding domains with totally different principles, are combined together through our proposed angle multiplexing framework, leading to multiplexed printings with hundreds of channels. Based on such approach, we experimentally encode respectively 25 gray scale printings into 25 angles and even 8 gray scale videos into 8 angles with a phase-only spatial light modulator. As a bridge between printings and holograms, our method allows to generate printings combining various holographic methods. Beneficial from this, we demonstrate a gradient metasurface based 324 channel printing which multiplexes angles, polarizations and wavelengths simultaneously. Our work paves the way to flexibly angle-dependent printing display and massively multiplexed encryption systems.

physics.optics↗

arXiv2022

Silicon Metasurface Embedded Fabry-Perot Cavity Enables High Quality Transmission Structural Color

While nanoscale color generations have been studied for years, the high performance transmission structural color, simultaneously equipped with large gamut, high resolution, and optical multiplexing abilities, still remains as a hanging issue. Here, a silicon metasurface embedded Fabry-Pérot cavity is demonstrated to address this problem. By changing the planar geometries of metasurface units, the cavities provide transmission colors with 194% sRGB gamut coverage and 141111 DPI resolution, along with more than 300% enhanced angular tolerance. Such high density allows two-dimensional color mixing at diffraction limit scale. Beneficial from the polarization manipulation capacity of the metasurface, arbitrary color arrangements between cyan and red for two orthogonal linear polarizations are also realized. Our proposed cavities can be used in filters, printings, optical storages and many other applications in need of high quality and density colors.

physics.optics↗

arXiv2022

OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving

Accurate sensor calibration is a prerequisite for multi-sensor perception and localization systems for autonomous vehicles. The intrinsic parameter calibration of the sensor is to obtain the mapping relationship inside the sensor, and the extrinsic parameter calibration is to transform two or more sensors into a unified spatial coordinate system. Most sensors need to be calibrated after installation to ensure the accuracy of sensor measurements. To this end, we present OpenCalib, a calibration toolbox that contains a rich set of various sensor calibration methods. OpenCalib covers manual calibration tools, automatic calibration tools, factory calibration tools, and online calibration tools for different application scenarios. At the same time, to evaluate the calibration accuracy and subsequently improve the accuracy of the calibration algorithm, we released a corresponding benchmark dataset. This paper introduces various features and calibration methods of this toolbox. To our knowledge, this is the first open-sourced calibration codebase containing the full set of autonomous-driving-related calibration approaches in this area. We wish that the toolbox could be helpful to autonomous driving researchers. We have open-sourced our code on GitHub to benefit the community. Code is available at https://github.com/PJLab-ADG/SensorsCalibration.

cs.RO↗