Searcharxiv⌕ Search

arXiv subjects

Hao Zheng

Publications and source records attributed to Hao Zheng.

At least 145 records · Page 8Linked to original sources
arXiv2023

High-throughput combinatorial approach expedites the synthesis of a lead-free relaxor ferroelectric system

Developing novel lead-free ferroelectric materials is crucial for next-generation microelectronic technologies that are energy efficient and environment friendly. However, materials discovery and property optimization are typically time-consuming due to the limited throughput of traditional synthesis methods. In this work, we use a high-throughput combinatorial synthesis approach to fabricate lead-free ferroelectric superlattices and solid solutions of (Ba0.7Ca0.3)TiO3 (BCT) and Ba(Zr0.2Ti0.8)O3 (BZT) phases with continuous variation of composition and layer thickness. High-resolution X-ray diffraction (XRD) and analytical scanning transmission electron microscopy (STEM) demonstrate high film quality and well-controlled compositional gradients. Ferroelectric and dielectric property measurements identify the optimal property point achieved at the morphotropic phase boundary (MPB) with a composition of 48BZT-52BCT. Displacement vector maps reveal that ferroelectric domain sizes are tunable by varying {BCT-BZT}N superlattice geometry. This high-throughput synthesis approach can be applied to many other material systems to expedite new materials discovery and properties optimization, allowing for the exploration of a large area of phase space within a single growth.

cond-mat.mtrl-sci↗
arXiv2023

MetaDefa: Meta-learning based on Domain Enhancement and Feature Alignment for Single Domain Generalization

The single domain generalization(SDG) based on meta-learning has emerged as an effective technique for solving the domain-shift problem. However, the inadequate match of data distribution between source and augmented domains and difficult separation of domain-invariant features from domain-related features make SDG model hard to achieve great generalization. Therefore, a novel meta-learning method based on domain enhancement and feature alignment (MetaDefa) is proposed to improve the model generalization performance. First, the background substitution and visual corruptions techniques are used to generate diverse and effective augmented domains. Then, the multi-channel feature alignment module based on class activation maps and class agnostic activation maps is designed to effectively extract adequate transferability knowledge. In this module, domain-invariant features can be fully explored by focusing on similar target regions between source and augmented domains feature space and suppressing the feature representation of non-similar target regions. Extensive experiments on two publicly available datasets show that MetaDefa has significant generalization performance advantages in unknown multiple target domains.

cs.CV↗
arXiv2023

Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification

In current synthetic aperture radar (SAR) object classification, one of the major challenges is the severe overfitting issue due to the limited dataset (few-shot) and noisy data. Considering the advantages of knowledge distillation as a learned label smoothing regularization, this paper proposes a novel Double Reverse Regularization Network based on Self-Knowledge Distillation (DRRNet-SKD). Specifically, through exploring the effect of distillation weight on the process of distillation, we are inspired to adopt the double reverse thought to implement an effective regularization network by combining offline and online distillation in a complementary way. Then, the Adaptive Weight Assignment (AWA) module is designed to adaptively assign two reverse-changing weights based on the network performance, allowing the student network to better benefit from both teachers. The experimental results on OpenSARShip and FUSAR-Ship demonstrate that DRRNet-SKD exhibits remarkable performance improvement on classical CNNs, outperforming state-of-the-art self-knowledge distillation methods.

cs.CV↗
arXiv2023

Can Machine Learning Uncover Insights into Vehicle Travel Demand from Our Built Environment?

In this paper, we propose a machine learning-based approach to address the lack of ability for designers to optimize urban land use planning from the perspective of vehicle travel demand. Research shows that our computational model can help designers quickly obtain feedback on the vehicle travel demand, which includes its total amount and temporal distribution based on the urban function distribution designed by the designers. It also assists in design optimization and evaluation of the urban function distribution from the perspective of vehicle travel. We obtain the city function distribution information and vehicle hours traveled (VHT) information by collecting the city point-of-interest (POI) data and online vehicle data. The artificial neural networks (ANNs) with the best performance in prediction are selected. By using data sets collected in different regions for mutual prediction and remapping the predictions onto a map for visualization, we evaluate the extent to which the computational model sees use across regions in an attempt to reduce the workload of future urban researchers. Finally, we demonstrate the application of the computational model to help designers obtain feedback on vehicle travel demand in the built environment and combine it with genetic algorithms to optimize the current state of the urban environment to provide recommendations to designers.

cs.LG↗
arXiv2023

Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification

The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset. However, in practice, the base and the target datasets of few-shot classification are usually from different domains, which is the problem of cross-domain few-shot classification. We tackle this problem by making a small proportion of unlabeled images in the target domain accessible in the training stage. In this setup, even though the base data are sufficient and labeled, the large domain shift still makes transferring the knowledge from the base dataset difficult. We meticulously design a cross-level knowledge distillation method, which can strengthen the ability of the model to extract more discriminative features in the target dataset by guiding the network's shallow layers to learn higher-level information. Furthermore, in order to alleviate the overfitting in the evaluation stage, we propose a feature denoising operation which can reduce the feature redundancy and mitigate overfitting. Our approach can surpass the previous state-of-the-art method, Dynamic-Distillation, by 5.44% on 1-shot and 1.37% on 5-shot classification tasks on average in the BSCD-FSL benchmark. The implementation code will be available at https://github.com/jarucezh/cldfd.

cs.CV↗
arXiv2023

Topological edge and corner states in Bi fractals on InSb

Topological materials hosting metallic edges characterized by integer quantized conductivity in an insulating bulk have revolutionized our understanding of transport in matter. The topological protection of these edge states is based on symmetries and dimensionality. However, only integer-dimensional models have been classified, and the interplay of topology and fractals, which may have a non-integer dimension, remained largely unexplored. Quantum fractals have recently been engineered in metamaterials, but up to present no topological states were unveiled in fractals realized in real materials. Here, we show theoretically and experimentally that topological edge and corner modes arise in fractals formed upon depositing thin layers of bismuth on an indium antimonide substrate. Scanning tunneling microscopy reveals the appearance of (nearly) zero-energy modes at the corners of Sierpiński triangles, as well as the formation of outer and inner edge modes at higher energies. Unexpectedly, a robust and sharp depleted mode appears at the outer and inner edges of the samples at negative bias voltages. The experimental findings are corroborated by theoretical calculations in the framework of a continuum muffin-tin and a lattice tight-binding model. The stability of the topological features to the introduction of a Rashba spin-orbit coupling and disorder is discussed. This work opens the perspective to novel electronics in real materials at non-integer dimensions with robust and protected topological states.

cond-mat.mes-hall↗
arXiv2023

Electronic band reconstruction across the insulator-metal transition in colossal magnetoresistive EuCd2P2

While colossal magnetoresistance (CMR) in Eu-based compounds is often associated with strong spin-carrier interactions, the underlying reconstruction of the electronic bands is much less understood from spectroscopic experiments. Here using angle-resolved photoemission, we directly observe an electronic band reconstruction across the insulator-metal (and magnetic) transition in the recently discovered CMR compound EuCd2P2. This transition is manifested by a large magnetic band splitting associated with the magnetic order, as well as unusual energy shifts of the valence bands: both the large ordered moment of Eu and carrier localization in the paramagnetic phase are crucial. Our results provide spectroscopic evidence for an electronic structure reconstruction underlying the enormous CMR observed in EuCd2P2, which could be important for understanding Eu-based CMR materials, as well as designing CMR materials based on large-moment rare-earth magnets.

cond-mat.mtrl-sci↗
arXiv2023

Categories of quantum liquids I

We develop a mathematical theory of separable higher categories based on Gaiotto and Johnson-Freyd's work on condensation completion. Based on this theory, we prove some fundamental results on $E_m$-multi-fusion higher categories and their higher centers. We also outline a theory of unitary higher categories based on a $*$-version of condensation completion. After these mathematical preparations, based on the idea of topological Wick rotation, we develop a unified mathematical theory of all quantum liquids, which include topological orders, SPT/SET orders, symmetry-breaking orders and CFT-like gapless phases. We explain that a quantum liquid consists of two parts, the topological skeleton and the local quantum symmetry, and show that all $n$D quantum liquids form a $*$-condensation complete higher category whose equivalence type can be computed explicitly from a simple coslice 1-category.

hep-th↗
arXiv2023

AutoModel: Automatic Synthesis of Models from Communication Traces of SoC Designs

Modeling system-level behaviors of intricate System-on-Chip (SoC) designs is crucial for design analysis, testing, and validation. However, the complexity and volume of SoC traces pose significant challenges in this task. This paper proposes an approach to automatically infer concise and abstract models from SoC communication traces, capturing the system-level protocols that govern message exchange and coordination between design blocks for various system functions. This approach, referred to as model synthesis, constructs a causality graph with annotations obtained from the SoC traces. The annotated causality graph represents all potential causality relations among messages under consideration. Next, a constraint satisfaction problem is formulated from the causality graph, which is then solved by a satisfiability modulo theories (SMT) solver to find satisfying solutions. Finally, finite state models are extracted from the generated solutions, which can be used to explain and understand the input traces. The proposed approach is validated through experiments using synthetic traces obtained from simulating a transaction-level model of a multicore SoC design and traces collected from running real programs on a realistic multicore SoC modeled with gem5.

cs.LO↗
arXiv2023

AC-Norm: Effective Tuning for Medical Image Analysis via Affine Collaborative Normalization

Driven by the latest trend towards self-supervised learning (SSL), the paradigm of "pretraining-then-finetuning" has been extensively explored to enhance the performance of clinical applications with limited annotations. Previous literature on model finetuning has mainly focused on regularization terms and specific policy models, while the misalignment of channels between source and target models has not received sufficient attention. In this work, we revisited the dynamics of batch normalization (BN) layers and observed that the trainable affine parameters of BN serve as sensitive indicators of domain information. Therefore, Affine Collaborative Normalization (AC-Norm) is proposed for finetuning, which dynamically recalibrates the channels in the target model according to the cross-domain channel-wise correlations without adding extra parameters. Based on a single-step backpropagation, AC-Norm can also be utilized to measure the transferability of pretrained models. We evaluated AC-Norm against the vanilla finetuning and state-of-the-art fine-tuning methods on transferring diverse pretrained models to the diabetic retinopathy grade classification, retinal vessel segmentation, CT lung nodule segmentation/classification, CT liver-tumor segmentation and MRI cardiac segmentation tasks. Extensive experiments demonstrate that AC-Norm unanimously outperforms the vanilla finetuning by up to 4% improvement, even under significant domain shifts where the state-of-the-art methods bring no gains. We also prove the capability of AC-Norm in fast transferability estimation. Our code is available at https://github.com/EndoluminalSurgicalVision-IMR/ACNorm.

cs.CV↗
arXiv2023

Gait Cycle-Inspired Learning Strategy for Continuous Prediction of Knee Joint Trajectory from sEMG

Predicting lower limb motion intent is vital for controlling exoskeleton robots and prosthetic limbs. Surface electromyography (sEMG) attracts increasing attention in recent years as it enables ahead-of-time prediction of motion intentions before actual movement. However, the estimation performance of human joint trajectory remains a challenging problem due to the inter- and intra-subject variations. The former is related to physiological differences (such as height and weight) and preferred walking patterns of individuals, while the latter is mainly caused by irregular and gait-irrelevant muscle activity. This paper proposes a model integrating two gait cycle-inspired learning strategies to mitigate the challenge for predicting human knee joint trajectory. The first strategy is to decouple knee joint angles into motion patterns and amplitudes former exhibit low variability while latter show high variability among individuals. By learning through separate network entities, the model manages to capture both the common and personalized gait features. In the second, muscle principal activation masks are extracted from gait cycles in a prolonged walk. These masks are used to filter out components unrelated to walking from raw sEMG and provide auxiliary guidance to capture more gait-related features. Experimental results indicate that our model could predict knee angles with the average root mean square error (RMSE) of 3.03(0.49) degrees and 50ms ahead of time. To our knowledge this is the best performance in relevant literatures that has been reported, with reduced RMSE by at least 9.5%.

cs.RO↗
arXiv2023

HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding

Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD - the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations. Specifically, HA-ViD captures diverse collaboration patterns of real-world assembly, natural human behaviors and learning progression during assembly, and granulate action annotations to subject, action verb, manipulated object, target object, and tool. We provide 3222 multi-view, multi-modality videos (each video contains one assembly task), 1.5M frames, 96K temporal labels and 2M spatial labels. We benchmark four foundational video understanding tasks: action recognition, action segmentation, object detection and multi-object tracking. Importantly, we analyze their performance for comprehending knowledge in assembly progress, process efficiency, task collaboration, skill parameters and human intention. Details of HA-ViD is available at: https://iai-hrc.github.io/ha-vid.

cs.CV↗
arXiv2023

Caption Anything: Interactive Image Description with Diverse Multimodal Controls

Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e.g.}$, looking at the specified regions or telling in a particular text style. State-of-the-art methods are trained on annotated pairs of input controls and output captions. However, the scarcity of such well-annotated multimodal data largely limits their usability and scalability for interactive AI systems. Leveraging unimodal instruction-following foundation models is a promising alternative that benefits from broader sources of data. In this paper, we present Caption AnyThing (CAT), a foundation model augmented image captioning framework supporting a wide range of multimodel controls: 1) visual controls, including points, boxes, and trajectories; 2) language controls, such as sentiment, length, language, and factuality. Powered by Segment Anything Model (SAM) and ChatGPT, we unify the visual and language prompts into a modularized framework, enabling the flexible combination between different controls. Extensive case studies demonstrate the user intention alignment capabilities of our framework, shedding light on effective user interaction modeling in vision-language applications. Our code is publicly available at https://github.com/ttengwang/Caption-Anything.

cs.CV↗
arXiv2023

Heterogeneous field response of hierarchical polar laminates in relaxor ferroelectrics

Relaxor ferroelectrics are a class of materials that are widely perceived as deriving their exotic properties from structural heterogeneities. Understanding the microscopic origin of the superior electromechanical response requires knowledge not only concerning the formation of polar nanodomains (PNDs) built from individual atoms but more importantly the spatial distribution of PNDs over longer distances. The mesoscale PND arrangement is shaped by the interactions between these domains and, in turn, dictates the electric-field driven PND response directly relevant to the macroscopic material properties. Here, we show the emergence of mesoscale lattice order that we name "polar laminates" in the canonical relaxor ferroelectric 0.68PbMg$_{1/3}$Nb$_{2/3}$O$_{3}$-0.32PbTiO$_{3}$ (PMN-0.32PT) using X-ray coherent nano-diffraction. These laminates are nematic with a size of ~350 nm and arise from the staggered arrangement of ~13 nm monoclinic PNDs along the <110> of the pseudocubic lattice. The spatial distribution of c-axis strain is directly correlated with the tilting of the PNDs and is most prominent between the laminates. Further operando nano-diffraction studies demonstrate heterogeneous electric-field-driven responses. The most active regions tend to reside inside the laminates while the spatial pinning centers are between the laminates. This observation reveals the hierarchical assembly of lattice order as a novel form of electron and lattice self-organization in heterogenous materials and establishes the role of such mesoscale spatial arrangement in connecting the nanoscale heterogeneity and macroscopic material properties. These findings provide a guiding principle for the design and optimization of future relaxors and may shed light on the existence of similar behavior in a wide range of quantum and functional materials.

cond-mat.mtrl-sci↗
arXiv2023

Multi-site, Multi-domain Airway Tree Modeling (ATM'22): A Public Benchmark for Pulmonary Airway Segmentation

Open international challenges are becoming the de facto standard for assessing computer vision and image analysis algorithms. In recent years, new methods have extended the reach of pulmonary airway segmentation that is closer to the limit of image resolution. Since EXACT'09 pulmonary airway segmentation, limited effort has been directed to quantitative comparison of newly emerged algorithms driven by the maturity of deep learning based approaches and clinical drive for resolving finer details of distal airways for early intervention of pulmonary diseases. Thus far, public annotated datasets are extremely limited, hindering the development of data-driven methods and detailed performance evaluation of new algorithms. To provide a benchmark for the medical imaging community, we organized the Multi-site, Multi-domain Airway Tree Modeling (ATM'22), which was held as an official challenge event during the MICCAI 2022 conference. ATM'22 provides large-scale CT scans with detailed pulmonary airway annotation, including 500 CT scans (300 for training, 50 for validation, and 150 for testing). The dataset was collected from different sites and it further included a portion of noisy COVID-19 CTs with ground-glass opacity and consolidation. Twenty-three teams participated in the entire phase of the challenge and the algorithms for the top ten teams are reviewed in this paper. Quantitative and qualitative results revealed that deep learning models embedded with the topological continuity enhancement achieved superior performance in general. ATM'22 challenge holds as an open-call design, the training data and the gold standard evaluation are available upon successful registration via its homepage.

eess.IV↗
arXiv2023

Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment

Pre-trained vision-language models have inspired much research on few-shot learning. However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant information in images, and (2) the alignment between the visual and language feature distributions is difficult. To deal with the distraction problem, we propose a Selective Attack module, which consists of trainable adapters that generate spatial attention maps of images to guide the attacks on class-irrelevant image areas. By messing up these areas, the critical features are captured and the visual distributions of image features are calibrated. To better align the visual and language feature distributions that describe the same object class, we propose a cross-modal distribution alignment module, in which we introduce a vision-language prototype for each class to align the distributions, and adopt the Earth Mover's Distance (EMD) to optimize the prototypes. For efficient computation, the upper bound of EMD is derived. In addition, we propose an augmentation strategy to increase the diversity of the images and the text prompts, which can reduce overfitting to the few-shot training images. Extensive experiments on 11 datasets demonstrate that our method consistently outperforms prior arts in few-shot learning. The implementation code will be available at https://github.com/bhrqw/SADA.

cs.CV↗
arXiv2023

CageViT: Convolutional Activation Guided Efficient Vision Transformer

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of Transformers have been proposed to accelerate computation or reduce memory consumption while preserving performance. This paper presents an efficient vision Transformer, called CageViT, that is guided by convolutional activation to reduce computation. Our CageViT, unlike current Transformers, utilizes a new encoder to handle the rearranged tokens, bringing several technical contributions: 1) Convolutional activation is used to pre-process the token after patchifying the image to select and rearrange the major tokens and minor tokens, which substantially reduces the computation cost through an additional fusion layer. 2) Instead of using the class activation map of the convolutional model directly, we design a new weighted class activation to lower the model requirements. 3) To facilitate communication between major tokens and fusion tokens, Gated Linear SRA is proposed to further integrate fusion tokens into the attention mechanism. We perform a comprehensive validation of CageViT on the image classification challenge. Experimental results demonstrate that the proposed CageViT outperforms the most recent state-of-the-art backbones by a large margin in terms of efficiency, while maintaining a comparable level of accuracy (e.g. a moderate-sized 43.35M model trained solely on 224 x 224 ImageNet-1K can achieve Top-1 accuracy of 83.4% accuracy).

cs.CV↗
arXiv2023

SurfNN: Joint Reconstruction of Multiple Cortical Surfaces from Magnetic Resonance Images

To achieve fast, robust, and accurate reconstruction of the human cortical surfaces from 3D magnetic resonance images (MRIs), we develop a novel deep learning-based framework, referred to as SurfNN, to reconstruct simultaneously both inner (between white matter and gray matter) and outer (pial) surfaces from MRIs. Different from existing deep learning-based cortical surface reconstruction methods that either reconstruct the cortical surfaces separately or neglect the interdependence between the inner and outer surfaces, SurfNN reconstructs both the inner and outer cortical surfaces jointly by training a single network to predict a midthickness surface that lies at the center of the inner and outer cortical surfaces. The input of SurfNN consists of a 3D MRI and an initialization of the midthickness surface that is represented both implicitly as a 3D distance map and explicitly as a triangular mesh with spherical topology, and its output includes both the inner and outer cortical surfaces, as well as the midthickness surface. The method has been evaluated on a large-scale MRI dataset and demonstrated competitive cortical surface reconstruction performance.

eess.IV↗