arXiv subjects

Yun Cheng

Publications and source records attributed to Yun Cheng.

At least 37 records · Page 2Linked to original sources

arXiv2024

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present the Localization and Focus Vision Transformer (LF-ViT). This model operates by strategically curtailing computational demands without impinging on performance. In the Localization phase, a reduced-resolution image is processed; if a definitive prediction remains elusive, our pioneering Neighborhood Global Class Attention (NGCA) mechanism is triggered, effectively identifying and spotlighting class-discriminative regions based on initial findings. Subsequently, in the Focus phase, this designated region is used from the original image to enhance recognition. Uniquely, LF-ViT employs consistent parameters across both phases, ensuring seamless end-to-end optimization. Our empirical tests affirm LF-ViT's prowess: it remarkably decreases Deit-S's FLOPs by 63\% and concurrently amplifies throughput twofold. Code of this project is at https://github.com/edgeai1/LF-ViT.git.

cs.CV↗

arXiv2023

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

The recent explosion of interest in multimodal applications has resulted in a wide selection of datasets and methods for representing and integrating information from different modalities. Despite these empirical advances, there remain fundamental research questions: How can we quantify the interactions that are necessary to solve a multimodal task? Subsequently, what are the most suitable multimodal models to capture these interactions? To answer these questions, we propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy relating input modalities with an output task. We term these three measures as the PID statistics of a multimodal distribution (or PID for short), and introduce two new estimators for these PID statistics that scale to high-dimensional distributions. To validate PID estimation, we conduct extensive experiments on both synthetic datasets where the PID is known and on large-scale multimodal benchmarks where PID estimations are compared with human annotations. Finally, we demonstrate their usefulness in (1) quantifying interactions within multimodal datasets, (2) quantifying interactions captured by multimodal models, (3) principled approaches for model selection, and (4) three real-world case studies engaging with domain experts in pathology, mood prediction, and robotic perception where our framework helps to recommend strong multimodal models for each application.

cs.LG↗

arXiv2023

Transient dynamics of the phase transition in VO2 revealed by mega electron-volt ultrafast electron diffraction

Vanadium dioxide (VO2) exhibits an insulator-to-metal transition accompanied by a structural transition near room temperature. This transition can be triggered by an ultrafast laser pulse. Exotic transient states, such as a metallic state without structural transition, were also proposed. These unique characteristics let VO2 have great potential in thermal switchable devices and photonic applications. Although great efforts have been made, the atomic pathway during the photoinduced phase transition is still not clear. Here, we synthesized freestanding quasi-single-crystal VO2 films and examined their photoinduced structural phase transition with mega-electron-volt ultrafast electron diffraction. Leveraging the high signal-to-noise ratio and high temporal resolution, we observe that the disappearance of vanadium dimers and zigzag chains does not coincide with the transformation of crystal symmetry. After photoexcitation, the initial structure is strongly modified within 200 femtoseconds, resulting in a transient monoclinic structure without vanadium dimers and zigzag chains. Then, it continues to evolve to the final tetragonal structure in approximately 5 picoseconds. In addition, only one laser fluence threshold instead of two thresholds suggested in polycrystalline samples was observed in our quasi-single-crystal samples. Our findings provide new essential information for a comprehensive understanding of the photoinduced ultrafast phase transition in VO2.

cond-mat.mtrl-sci↗

arXiv2023

Multimodal Fusion Interactions: A Study of Human and Automatic Quantification

In order to perform multimodal fusion of heterogeneous signals, we need to understand their interactions: how each modality individually provides information useful for a task and how this information changes in the presence of other modalities. In this paper, we perform a comparative study of how humans annotate two categorizations of multimodal interactions: (1) partial labels, where different annotators annotate the label given the first, second, and both modalities, and (2) counterfactual labels, where the same annotator annotates the label given the first modality before asking them to explicitly reason about how their answer changes when given the second. We further propose an alternative taxonomy based on (3) information decomposition, where annotators annotate the degrees of redundancy: the extent to which modalities individually and together give the same predictions, uniqueness: the extent to which one modality enables a prediction that the other does not, and synergy: the extent to which both modalities enable one to make a prediction that one would not otherwise make using individual modalities. Through experiments and annotations, we highlight several opportunities and limitations of each approach and propose a method to automatically convert annotations of partial and counterfactual labels to information decomposition, yielding an accurate and efficient method for quantifying multimodal interactions.

cs.LG↗

arXiv2023

MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiZoo, a public toolkit consisting of standardized implementations of > 20 core multimodal algorithms and MultiBench, a large-scale benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. Together, these provide an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. To enable holistic evaluation, we offer a comprehensive methodology to assess (1) generalization, (2) time and space complexity, and (3) modality robustness. MultiBench paves the way towards a better understanding of the capabilities and limitations of multimodal models, while ensuring ease of use, accessibility, and reproducibility. Our toolkits are publicly available, will be regularly updated, and welcome inputs from the community.

cs.LG↗

arXiv2023

CamDiff: Camouflage Image Augmentation via Diffusion Model

The burgeoning field of camouflaged object detection (COD) seeks to identify objects that blend into their surroundings. Despite the impressive performance of recent models, we have identified a limitation in their robustness, where existing methods may misclassify salient objects as camouflaged ones, despite these two characteristics being contradictory. This limitation may stem from lacking multi-pattern training images, leading to less saliency robustness. To address this issue, we introduce CamDiff, a novel approach inspired by AI-Generated Content (AIGC) that overcomes the scarcity of multi-pattern training images. Specifically, we leverage the latent diffusion model to synthesize salient objects in camouflaged scenes, while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training (CLIP) model to prevent synthesis failures and ensure the synthesized object aligns with the input prompt. Consequently, the synthesized image retains its original camouflage label while incorporating salient objects, yielding camouflage samples with richer characteristics. The results of user studies show that the salient objects in the scenes synthesized by our framework attract the user's attention more; thus, such samples pose a greater challenge to the existing COD models. Our approach enables flexible editing and efficient large-scale dataset generation at a low cost. It significantly enhances COD baselines' training and testing phases, emphasizing robustness across diverse domains. Our newly-generated datasets and source code are available at https://github.com/drlxj/CamDiff.

cs.CV↗

arXiv2023

Dynamic Graph Neural Network with Adaptive Edge Attributes for Air Quality Predictions

Air quality prediction is a typical spatio-temporal modeling problem, which always uses different components to handle spatial and temporal dependencies in complex systems separately. Previous models based on time series analysis and Recurrent Neural Network (RNN) methods have only modeled time series while ignoring spatial information. Previous GCNs-based methods usually require providing spatial correlation graph structure of observation sites in advance. The correlations among these sites and their strengths are usually calculated using prior information. However, due to the limitations of human cognition, limited prior information cannot reflect the real station-related structure or bring more effective information for accurate prediction. To this end, we propose a novel Dynamic Graph Neural Network with Adaptive Edge Attributes (DGN-AEA) on the message passing network, which generates the adaptive bidirected dynamic graph by learning the edge attributes as model parameters. Unlike prior information to establish edges, our method can obtain adaptive edge information through end-to-end training without any prior information. Thus reduced the complexity of the problem. Besides, the hidden structural information between the stations can be obtained as model by-products, which can help make some subsequent decision-making analyses. Experimental results show that our model received state-of-the-art performance than other baselines.

cs.LG↗

arXiv2022

Typical values of extremal-weight combinatorial structures with independent symmetric weights

Suppose that the edges of a complete graph are assigned weights independently at random and we ask for the weight of the minimal-weight spanning tree, or perfect matching, or Hamiltonian cycle. For these and several other common optimisation problems, we establish asymptotically tight bounds when the weights are independent copies of a symmetric random variable (satisfying a mild condition on tail probabilities), in particular when the weights are Gaussian.

math.CO↗

arXiv2022

Ultrafast formation of topological defects in a 2D charge density wave

Topological defects play a key role in nonequilibrium phase transitions, ranging from birth of the early universe to quantum critical behavior of ultracold atoms. In solids, transient defects are known to generate a variety of hidden orders not accessible in equilibrium, but how defects are formed at the nanometer lengthscale and femtosecond timescale remains unknown. Here, we employ an intense laser pulse to create topological defects in a 2D charge density wave, and track their morphology and dynamics with ultrafast electron diffraction. Leveraging its high temporal resolution and sensitivity in detecting weak diffuse signals, we discover a dual-stage growth of 1D domain walls within 1 ps, a process not dictated by the order parameter amplitude but instead mediated by a nonthermal population of longitudinal optical phonons. Our work provides a framework for ultrafast engineering of topological defects based on selective excitation of collective modes, opening new avenues for dynamical control of nonequilibrium phases in correlated materials.

cond-mat.mtrl-sci↗

arXiv2022

Light-induced dimension crossover in 1T-TiSe$_2$ dictated by excitonic correlations

In low-dimensional systems with strong electronic correlations, the application of an ultrashort laser pulse often yields novel phases that are otherwise inaccessible. The central challenge in understanding such phenomena is to determine how dimensionality and many-body correlations together govern the pathway of a non-adiabatic transition. To this end, we examine a layered compound, 1T-TiSe$_2$, whose three-dimensional charge-density-wave (3D CDW) state also features exciton condensation due to strong electron-hole interactions. We find that photoexcitation suppresses the equilibrium 3D CDW while creating a nonequilibrium 2D CDW. Remarkably, the dimension reduction does not occur unless bound electron-hole pairs are broken. This relation suggests that excitonic correlations maintain the out-of-plane CDW coherence, settling a long-standing debate over their role in the CDW transition. Our findings demonstrate how optical manipulation of electronic interaction enables one to control the dimensionality of a broken-symmetry order, paving the way for realizing other emergent states in strongly correlated systems.

cond-mat.str-el↗

arXiv2021

MultiBench: Multiscale Benchmarks for Multimodal Representation Learning

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics, finance, human-computer interaction, and healthcare. Unfortunately, multimodal research has seen limited resources to study (1) generalization across domains and modalities, (2) complexity during training and inference, and (3) robustness to noisy and missing modalities. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiBench, a systematic and unified large-scale benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. MultiBench provides an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. To enable holistic evaluation, MultiBench offers a comprehensive methodology to assess (1) generalization, (2) time and space complexity, and (3) modality robustness. MultiBench introduces impactful challenges for future research, including scalability to large-scale multimodal datasets and robustness to realistic imperfections. To accompany this benchmark, we also provide a standardized implementation of 20 core approaches in multimodal learning. Simply applying methods proposed in different research areas can improve the state-of-the-art performance on 9/15 datasets. Therefore, MultiBench presents a milestone in unifying disjoint efforts in multimodal research and paves the way towards a better understanding of the capabilities and limitations of multimodal models, all the while ensuring ease of use, accessibility, and reproducibility. MultiBench, our standardized code, and leaderboards are publicly available, will be regularly updated, and welcomes inputs from the community.

cs.LG↗

arXiv2021

Optical manipulation of electronic dimensionality in a quantum material

Exotic phenomenon can be achieved in quantum materials by confining electronic states into two dimensions. For example, relativistic fermions are realised in a single layer of carbon atoms, the quantized Hall effect can result from two-dimensional (2D) systems, and the superconducting transition temperature can be enhanced significantly in a one-atomic-layer material. Ordinarily, 2D electronic system can be obtained by exfoliating the layered materials, growing monolayer materials on substrates, or establishing interfaces between different materials. Herein, we use femtosecond infrared laser pulses to invert the periodic lattice distortion sectionally in a three-dimensional (3D) charge density wave material, creating macroscopic domain walls of transient 2D ordered electronic states with exotic properties. The corresponding ultrafast electronic and lattice dynamics are captured by time- and angle-resolved photoemission spectroscopy and MeV ultrafast electron diffraction. Surprisingly, a novel energy gap state, which might be a signature of light-induced superconductivity, is identified in the photoinduced 2D domain wall near the surface. Such optical modulation of atomic motion is a new path to realise 2D electronic states and will be a new platform for creating novel phases in quantum materials.

cond-mat.str-el↗

arXiv2021

Interpretable and Transferable Models to Understand the Impact of Lockdown Measures on Local Air Quality

The COVID-19 related lockdown measures offer a unique opportunity to understand how changes in economic activity and traffic affect ambient air quality and how much pollution reduction potential can the society offer through digitalization and mobilitylimiting policies. In this work, we estimate pollution reduction over the lockdown period by using the measurements from ground air pollution monitoring stations, training a long-term prediction model and comparing its predictions to measured values over the lockdown month.We show that our models achieve state-of-the-art performance on the data from air pollution measurement stations in Switzerland and in China: evaluate up to -15.8% / +34.4% change in NO2 / PM10 in Zurich; -35.3 % / -3.5 % and -42.4 % / -34.7 % in NO2 / PM2.5 in Beijing and Wuhan respectively. Our reduction estimates are consistent with recent publications, yet in contrast to prior works, our method takes local weather into account. What can we learn from pollution emissions during lockdown? The lockdown period was too short to train meaningful models from scratch. To tackle this problem, we use transfer learning to newly fit only traffic-dependent variables. We show that the resulting models are accurate, suitable for an analysis of the post-lockdown period and capable of estimating the future air pollution reduction potential.

cs.LG↗

arXiv2020

Adaptive Loss-aware Quantization for Multi-bit Networks

We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms. We propose Adaptive Loss-aware Quantization (ALQ), a new MBN quantization pipeline that is able to achieve an average bitwidth below one-bit without notable loss in inference accuracy. Unlike previous MBN quantization solutions that train a quantizer by minimizing the error to reconstruct full precision weights, ALQ directly minimizes the quantization-induced error on the loss function involving neither gradient approximation nor full precision maintenance. ALQ also exploits strategies including adaptive bitwidth, smooth bitwidth reduction, and iterative trained quantization to allow a smaller network size without loss in accuracy. Experiment results on popular image datasets show that ALQ outperforms state-of-the-art compressed networks in terms of both storage and accuracy. Code is available at https://github.com/zqu1992/ALQ

cs.CV↗

arXiv2020

Achieving 50 femtosecond resolution in MeV ultrafast electron diffraction with a double bend achromat compressor

We propose and demonstrate a novel scheme to produce ultrashort and ultrastable MeV electron beam. In this scheme, the electron beam produced in a photocathode radio-frequency (rf) gun first expands under its own Coulomb force with which a positive energy chirp is imprinted in the beam longitudinal phase space. The beam is then sent through a double bend achromat with positive longitudinal dispersion where electrons at the bunch tail with lower energies follow shorter paths and thus catch up with the bunch head, leading to longitudinal bunch compression. We show that with optimized parameter sets, the whole beam path from the electron source to the compression point can be made isochronous such that the time of flight for the electron beam is immune to the fluctuations of rf amplitude. With a laser-driven THz deflector, the bunch length and arrival time jitter for a 20 fC beam after bunch compression are measured to be about 29 fs (FWHM) and 22 fs (FWHM), respectively. Such an ultrashort and ultrastable electron beam allows us to achieve 50 femtosecond (FWHM) resolution in MeV ultrafast electron diffraction where lattice oscillation at 2.6 THz corresponding to Bismuth A1g mode is clearly observed without correcting both the short-term timing jitter and long-term timing drift. Furthermore, oscillating weak diffuse scattering signal related to phonon coupling and decay is also clearly resolved thanks to the improved temporal resolution and increased electron flux. We expect that this technique will have a strong impact in emerging ultrashort electron beam based facilities and applications.

physics.acc-ph↗

arXiv2019

Terahertz oscilloscope for recording time information of ultrashort electron beams

We propose and demonstrate a Terahertz (THz) oscilloscope for recording time information of an ultrashort electron beam. By injecting a laser-driven THz pulse with circular polarization into a dielectric tube, the electron beam is swept helically such that the time information is uniformly encoded into the angular distribution that allows one to characterize both the temporal profile and timing jitter of an electron beam. The dynamic range of the measurement in such a configuration is significantly increased compared to deflection with a linearly polarized THz pulse. With this THz oscilloscope, nearly 50-fold longitudinal compression of a relativistic electron beam to about 15 fs (rms) is directly visualized with its arrival time determined with 3 fs accuracy. This technique bridges the gap between streaking of photoelectrons with optical lasers and deflection of relativistic electron beams with radio-frequency deflectors, and should have wide applications in many ultrashort electron beam based facilities.

physics.acc-ph↗

arXiv2015

The specific charged hadron multiplicity in ep and eD semi-inclusive deep-inelastic scattering in the PYTHIA and PACIAE models

We employed the PYTHIA 6.4 model and the extended parton and hadron cascade model PACIAE 2.2 to comparatively investigate the DIS normalized specific charged hadron multiplicity in the 27.6 GeV electron semi-inclusive deep-inelastic scattering off proton and deuteron. The PYTHIA and PACIAE results calculated with default model parameters not well and fairly well reproduce the corresponding HERMES data, respectively. In addition, we have discussed the effects of the differences between the PYTHIA and PACIAE models.

nucl-th↗

arXiv2014

Systematic study of elliptic flow parameter in the relativistic nuclear collisions at RHIC and LHC energies

We employed the new issue of a parton and hadron cascade model PACIAE 2.1 to systematically investigate the charged particle elliptic flow parameter $v_2$ in the relativistic nuclear collisions at RHIC and LHC energies. With randomly sampling the transverse momentum $x$ and $y$ components of the particles generated in string fragmentation on the circumference of an ellipse instead of circle originally, the calculated charged particle $v_2(η)$ and $v_2(p_T)$ fairly reproduce the corresponding experimental data in the Au+Au/Pb+Pb collisions at $\sqrt{s_{NN}}$=0.2/2.76 TeV. In addition, the charged particle $v_2(η)$ and $v_2(p_T)$ in the p+p collisions at $\sqrt s$=7 TeV as well as in the p+Au/p+Pb collisions at $\sqrt{s_{NN}}$=0.2/5.02 TeV are predicted.

nucl-th↗