arXiv subjects

Yiming Zhou

Publications and source records attributed to Yiming Zhou.

33 records · Page 2Linked to original sources

arXiv2024

Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networks

Deception detection is gaining increasing interest due to ethical and security concerns. This paper explores the application of convolutional neural networks for the purpose of multimodal deception detection. We use a dataset built by interviewing 104 subjects about two topics, with one truthful and one falsified response from each subject about each topic. In particular, we make three main contributions. First, we extract linguistic and physiological features from this data to train and construct the neural network models. Second, we propose a fused convolutional neural network model using both modalities in order to achieve an improved overall performance. Third, we compare our new approach with earlier methods designed for multimodal deception detection. We find that our system outperforms regular classification methods; our results indicate the feasibility of using neural networks for deception detection even in the presence of limited amounts of data.

cs.CL↗

arXiv2024

Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translation

Generative Adversarial Networks (GANs) have significantly advanced image processing, with Pix2Pix being a notable framework for image-to-image translation. This paper explores a novel application of Pix2Pix to transform abstract map images into realistic ground truth images, addressing the scarcity of such images crucial for domains like urban planning and autonomous vehicle training. We detail the Pix2Pix model's utilization for generating high-fidelity datasets, supported by a dataset of paired map and aerial images, and enhanced by a tailored training regimen. The results demonstrate the model's capability to accurately render complex urban features, establishing its efficacy and potential for broad real-world applications.

cs.CV↗

arXiv2024

Integrating AI in NDE: Techniques, Trends, and Further Directions

The digital transformation is fundamentally changing our industries, affecting planning, execution as well as monitoring of production processes in a wide range of application fields. With product line-ups becoming more and more versatile and diverse, the necessary inspection and monitoring sparks significant novel requirements on the corresponding Nondestructive Evaluation (NDE) systems. The establishment of increasingly powerful approaches to incorporate Artificial Intelligence (AI) may provide just the needed innovation to solve some of these challenges. In this paper we provide a comprehensive survey about the usage of AI methods in NDE in light of the recent innovations towards NDE 4.0. Since we cannot discuss each NDE modality in one paper, we limit our attention to magnetic methods, ultrasound, thermography, as well as optical inspection. In addition to reviewing recent AI developments in each field, we draw common connections by pointing out NDE-related tasks that have a common underlying mathematical problem and categorizing the state of the art according to the corresponding sub-tasks. In so doing, interdisciplinary connections are drawn that provide a more complete overall picture.

eess.SP↗

arXiv2024

DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM

SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mapping errors in real-world scenarios with dynamic interferences. To address these issues, we introduce DDN-SLAM, the first real-time dense dynamic neural implicit SLAM system integrating semantic features. To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed Gaussian distribution model. To avoid incorrect background removal, we propose a mapping strategy based on sparse point cloud sampling and background restoration. We propose a dynamic semantic loss to eliminate dynamic occlusions. Experimental results demonstrate that DDN-SLAM is capable of robustly tracking and producing high-quality reconstructions in dynamic environments, while appropriately preserving potential dynamic objects. Compared to existing neural implicit SLAM systems, the tracking results on dynamic datasets indicate an average 90% improvement in Average Trajectory Error (ATE) accuracy.

cs.CV↗

arXiv2024

Jointly Learning Selection Matrices For Transmitters, Receivers And Fourier Coefficients In Multichannel Imaging

Strategic subsampling has become a focal point due to its effectiveness in compressing data, particularly in the Full Matrix Capture (FMC) approach in ultrasonic imaging. This paper introduces the Joint Deep Probabilistic Subsampling (J-DPS) method, which aims to learn optimal selection matrices simultaneously for transmitters, receivers, and Fourier coefficients. This task-based algorithm is realized by introducing a specialized measurement model and integrating a customized Complex Learned FISTA (CL-FISTA) network. We propose a parallel network architecture, partitioned into three segments corresponding to the three matrices, all working toward a shared optimization objective with adjustable loss allocation. A synthetic dataset is designed to reflect practical scenarios, and we provide quantitative comparisons with a traditional CRB-based algorithm, standard DPS, and J-DPS.

eess.IV↗

arXiv2024

Proximal Dogleg Opportunistic Majorization for Nonconvex and Nonsmooth Optimization

We consider minimizing a function consisting of a quadratic term and a proximable term which is possibly nonconvex and nonsmooth. This problem is also known as scaled proximal operator. Despite its simple form, existing methods suffer from slow convergence or high implementation complexity or both. To overcome these limitations, we develop a fast and user-friendly second-order proximal algorithm. Key innovation involves building and solving a series of opportunistically majorized problems along a hybrid Newton direction. The approach directly uses the precise Hessian of the quadratic term, and calculates the inverse only once, eliminating the iterative numerical approximation of the Hessian, a common practice in quasi-Newton methods. The algorithm's convergence to a critical point is established, and local convergence rate is derived based on the Kurdyka-Lojasiewicz property of the objective function. Numerical comparisons are conducted on well-known optimization problems. The results demonstrate that the proposed algorithm not only achieves a faster convergence but also tends to converge to a better local optimum compare to benchmark algorithms.

math.OC↗

arXiv2024

Communication-Efficient Distributed Learning with Local Immediate Error Compensation

Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate. In this work, we propose the Local Immediate Error Compensated SGD (LIEC-SGD) optimization algorithm to break the above bottlenecks based on bidirectional compression and carefully designed compensation approaches. Specifically, the bidirectional compression technique is to reduce the communication cost, and the compensation technique compensates the local compression error to the model update immediately while only maintaining the global error variable on the server throughout the iterations to boost its efficacy. Theoretically, we prove that LIEC-SGD is superior to previous works in either the convergence rate or the communication cost, which indicates that LIEC-SGD could inherit the dual advantages from unidirectional compression and bidirectional compression. Finally, experiments of training deep neural networks validate the effectiveness of the proposed LIEC-SGD algorithm.

cs.LG↗

arXiv2023

Time Stretch with Continuous-Wave Lasers

A single-shot measurement technique for ultrafast phenomena with high throughput enables the capture of rare events within a short time scale, facilitating the exploration of rare ultrafast processes. Photonic time stretch stands out as a highly effective method for both detecting rapid events and achieving remarkable speed in imaging and ranging applications. The current time stretch method relies on costly passive mode-locked lasers with continuous and fixed spectra to capture fast transients and dilate their time scale using dispersion. This hinders the broad application of time stretch technology and presents synchronization challenges with ultrafast events for measurement. Here we report the first implementation of time stretch using continuous wave (CW) diode lasers with discrete and tunable spectra that are common in WDM optical communication. This approach offers the potential for more cost-effective and compact time stretch systems and simplifies laser synchronization with the input signal. Two different embodiments in the United States and Japan demonstrate the technique's operation and limitations, and potential applications to time stretch imaging and angular light scattering.

physics.optics↗

arXiv2023

PhyCV: The First Physics-inspired Computer Vision Library

PhyCV is the first computer vision library which utilizes algorithms directly derived from the equations of physics governing physical phenomena. The algorithms appearing in the current release emulate, in a metaphoric sense, the propagation of light through a physical medium with natural and engineered diffractive properties followed by coherent detection. Unlike traditional algorithms that are a sequence of hand-crafted empirical rules or deep learning algorithms that are usually data-driven and computationally heavy, physics-inspired algorithms leverage physical laws of nature as blueprints for inventing algorithms. PhyCV features low-dimensionality and high- efficiency, making it ideal for edge computing applications. We demonstrate real-time video processing on NVIDIA Jetson Nano using PhyCV. In addition, these algorithms have the potential to be implemented in real physical devices for fast and efficient computation in the form of analog computing. The open-sourced code is available at https://github.com/JalaliLabUCLA/phycv

eess.IV↗

arXiv2023

SimpleNet: A Simple Network for Image Anomaly Detection and Localization

We propose a simple and application-friendly network (called SimpleNet) for detecting and localizing anomalies. SimpleNet consists of four components: (1) a pre-trained Feature Extractor that generates local features, (2) a shallow Feature Adapter that transfers local features towards target domain, (3) a simple Anomaly Feature Generator that counterfeits anomaly features by adding Gaussian noise to normal features, and (4) a binary Anomaly Discriminator that distinguishes anomaly features from normal features. During inference, the Anomaly Feature Generator would be discarded. Our approach is based on three intuitions. First, transforming pre-trained features to target-oriented features helps avoid domain bias. Second, generating synthetic anomalies in feature space is more effective, as defects may not have much commonality in the image space. Third, a simple discriminator is much efficient and practical. In spite of simplicity, SimpleNet outperforms previous methods quantitatively and qualitatively. On the MVTec AD benchmark, SimpleNet achieves an anomaly detection AUROC of 99.6%, reducing the error by 55.5% compared to the next best performing model. Furthermore, SimpleNet is faster than existing methods, with a high frame rate of 77 FPS on a 3080ti GPU. Additionally, SimpleNet demonstrates significant improvements in performance on the One-Class Novelty Detection task. Code: https://github.com/DonaldRR/SimpleNet.

cs.CV↗

arXiv2022

Improving Levenberg-Marquardt Algorithm for Neural Networks

We explore the usage of the Levenberg-Marquardt (LM) algorithm for regression (non-linear least squares) and classification (generalized Gauss-Newton methods) tasks in neural networks. We compare the performance of the LM method with other popular first-order algorithms such as SGD and Adam, as well as other second-order algorithms such as L-BFGS , Hessian-Free and KFAC. We further speed up the LM method by using adaptive momentum, learning rate line search, and uphill step acceptance.

cs.LG↗

arXiv2020

Deep Learning Interference Cancellation in Wireless Networks

With the crowding of the electromagnetic spectrum and the shrinking cell size in wireless networks, crosstalk between base stations and users is a major problem. Although hand-crafted functional blocks and coding schemes are proven effective to guarantee reliable data transfer, currently deep learning-based approaches have drawn increasing attention in the communication system modeling. In this paper, we propose a Neural Network (NN) based signal processing technique that works with traditional DSP algorithms to overcome the interference problem in realtime. This technique doesn't require any feedback protocol between the receiver and transmitter which makes it very suitable for low-latency and high data-rate applications such as autonomy and augmented reality. While there has been recent work on the use of Reinforcement Learning (RL) in the control layer to manage and control the interference, our approach is novel in the sense that it introduces a neural network for signal processing at baseband data rate and in the physical layer. We demonstrate this "Deep Interference Cancellation" technique using a convolutional LSTM autoencoder. When applied to QAM-OFDM modulated data, the network produces significant improvement in the symbol error rate (SER). We further discuss the hardware implementation including latency, power consumption, memory requirements, and chip area.

eess.SP↗

arXiv2020

Deep Analog-to-Digital Converter for Wireless Communication

With the advent of the 5G wireless networks, achieving tens of gigabits per second throughputs and low, milliseconds, latency has become a reality. This level of performance will fuel numerous real-time applications, such as autonomy and augmented reality, where the computationally heavy tasks can be performed in the cloud. The increase in the bandwidth along with the use of dense constellations places a significant burden on the speed and accuracy of analog-to-digital converters (ADC). A popular approach to create wideband ADCs is utilizing multiple channels each operating at a lower speed in the time-interleaved fashion. However, an interleaved ADC comes with its own set of challenges. The parallel architecture is very sensitive to the inter-channel mismatch, timing jitter, clock skew between different ADC channels as well as the nonlinearity within individual channels. Consequently, complex post-calibration is required using digital signal processing (DSP) after the ADC. The traditional DSP calibration consumes a significant amount of power and its design requires knowledge of the source and type of errors which are becoming increasingly difficult to predict in nanometer CMOS processes. In this paper, instead of individually targeting each source of error, we utilize a deep learning algorithm to learn the complete and complex ADC behavior and to compensate for it in realtime. We demonstrate this "Deep ADC" technique on an 8G Sample/s 8-channel time-interleaved ADC with the QAM-OFDM modulated data. Simulation results for different QAM symbol constellations and OFDM subcarriers show dramatic improvements of approximately 5 bits in the dynamic range with a concomitant drastic reduction in symbol error rate. We further discuss the hardware implementation including latency, power consumption, memory requirements, and chip area.

eess.SP↗

arXiv2020

Accuracy and Resiliency of Analog Compute-in-Memory Inference Engines

Recently, analog compute-in-memory (CIM) architectures based on emerging analog non-volatile memory (NVM) technologies have been explored for deep neural networks (DNN) to improve energy efficiency. Such architectures, however, leverage charge conservation, an operation with infinite resolution, and thus are susceptible to errors. The computations in DNN realized by analog NVM thus have high uncertainty due to the device stochasticity. Several reports have demonstrated the use of analog NVM for CIM in a limited scale. It is unclear whether the uncertainties in computations will prohibit large-scale DNNs. To explore this critical issue of scalability, this paper first presents a simulation framework to evaluate the feasibility of large-scale DNNs based on CIM architecture and analog NVM. Simulation results show that DNNs trained for high-precision digital computing engines are not resilient against the uncertainty of the analog NVM devices. To avoid such catastrophic failures, this paper introduces the analog floating-point representation for the DNN, and the Hessian-Aware Stochastic Gradient Descent (HA-SGD) training algorithm to enhance the inference accuracy of trained DNNs. As a result of such enhancements, DNNs such as Wide ResNets for the CIFAR-100 image recognition problem are demonstrated to have significant performance improvements in accuracy without adding cost to the inference hardware.

eess.SP↗

arXiv2019

Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

Achieving good speed and accuracy trade-off on a target platform is very important in deploying deep neural networks in real world scenarios. However, most existing automatic architecture search approaches only concentrate on high performance. In this work, we propose an algorithm that can offer better speed/accuracy trade-off of searched networks, which is termed "Partial Order Pruning". It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off. Our algorithm explicitly takes profile information about the inference speed on the target platform into consideration. With the proposed algorithm, we present several Dongfeng (DF) networks that provide high accuracy and fast inference speed on various application GPU platforms. By further searching decoder architectures, our DF-Seg real-time segmentation networks yield state-of-the-art speed/accuracy trade-off on both the target embedded device and the high-end GPU.

cs.CV↗