Searcharxiv⌕ Search

arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 397 records · Page 22Linked to original sources
arXiv2023

Language-Assisted 3D Scene Understanding

The scale and quality of point cloud datasets constrain the advancement of point cloud learning. Recently, with the development of multi-modal learning, the incorporation of domain-agnostic prior knowledge from other modalities, such as images and text, to assist in point cloud feature learning has been considered a promising avenue. Existing methods have demonstrated the effectiveness of multi-modal contrastive training and feature distillation on point clouds. However, challenges remain, including the requirement for paired triplet data, redundancy and ambiguity in supervised features, and the disruption of the original priors. In this paper, we propose a language-assisted approach to point cloud feature learning (LAST-PCL), enriching semantic concepts through LLMs-based text enrichment. We achieve de-redundancy and feature dimensionality reduction without compromising textual priors by statistical-based and training-free significant feature selection. Furthermore, we also delve into an in-depth analysis of the impact of text contrastive training on the point cloud. Extensive experiments validate that the proposed method learns semantically meaningful point cloud features and achieves state-of-the-art or comparable performance in 3D semantic segmentation, 3D object detection, and 3D scene classification tasks.

cs.CV↗
arXiv2023

Nonlinear Time-History Analysis of Soil-Structure Systems Incorporating Frequency-Dependent Impedance Functions

To accurately analyze structures, soil-structure interaction effects must be taken into account. One approach is to create a complete finite element model of the full system wherein the soil is represented as a semi-infinite domain. This direct method is frequently adopted in research studies, but it is typically avoided in engineering practice due to the labor-intensive model development, and the high computational cost. In practice, soil-structure interaction analysis is mostly carried out through a substructure approach where the superstructure is modeled through a detailed model and is placed on a soil-foundation substructure which is represented by a system called impedance function. Then, the entire system is analyzed under foundation input motions. While the method is theoretically designed for linear-elastic behavior, it can be partially applied to nonlinear systems too. Although impedance functions for various soil and foundation configurations can be obtained from analytical, numerical, or experimental analyses, their implementation in the time-domain is not trivial because they are frequency-dependent. A simple solution for this problem has been to convert them to some physical models with frequency-independent components, but there is no straightforward way to connect these components. More importantly, the coefficients of these components could be non-physical parameters that cannot be modeled in software like OpenSEES. To resolve these problems, various alternative approaches have been proposed in the literature. In this project, we review some of the existing solutions and verify them through numerical examples. After extensive review and evaluation, the Hybrid Time Frequency Domain method seems a more practical solution with fewer stability issues. This method is implemented in Opensees to be used by researchers and practitioners.

cs.CE↗
arXiv2023

EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection

In the era where AI-generated content (AIGC) models can produce stunning and lifelike images, the lingering shadow of unauthorized reproductions and malicious tampering poses imminent threats to copyright integrity and information security. Current image watermarking methods, while widely accepted for safeguarding visual content, can only protect copyright and ensure traceability. They fall short in localizing increasingly realistic image tampering, potentially leading to trust crises, privacy violations, and legal disputes. To solve this challenge, we propose an innovative proactive forensics framework EditGuard, to unify copyright protection and tamper-agnostic localization, especially for AIGC-based editing methods. It can offer a meticulous embedding of imperceptible watermarks and precise decoding of tampered areas and copyright information. Leveraging our observed fragility and locality of image-into-image steganography, the realization of EditGuard can be converted into a united image-bit steganography issue, thus completely decoupling the training process from the tampering types. Extensive experiments demonstrate that our EditGuard balances the tamper localization accuracy, copyright recovery precision, and generalizability to various AIGC-based tampering methods, especially for image forgery that is difficult for the naked eye to detect. The project page is available at https://xuanyuzhang21.github.io/project/editguard/.

cs.CV↗
arXiv2023

Invisible Units Detection and Estimation Based on Random Matrix Theory

Invisible units mainly refer to small-scale units that are not monitored by, and thus are not visible to utilities. Integration of these invisible units into power systems does significantly affect the way in which a distribution grid is planned and operated. This paper, based on random matrix theory (RMT), proposes a statistical, data-driven framework to handle the massive grid data, in contrast to its deterministic, model-based counterpart. Combining the RMT-based data-mining framework with conventional techniques, some heuristics are derived as the solution to the invisible units detection and estimation task: linear eigenvalue statistic indicators (LESs) are suggested as the main ingredients of the solution; according to the statistical properties of LESs, the hypothesis testing is formulated to conduct change point detection in the high-dimensional space. The proposed method is promising for anomaly detection and pertinent to current distribution networks-it is capable of detecting invisible power usage and fraudulent behavior while even being able to locate the suspect's location. Case studies, using both simulated data and actual data, validate the proposed method.

stat.AP↗
arXiv2023

STAGER checklist: Standardized Testing and Assessment Guidelines for Evaluating Generative AI Reliability

Generative Artificial Intelligence (AI) holds immense potential in medical applications. Numerous studies have explored the efficacy of various generative AI models within healthcare contexts, but there is a lack of a comprehensive and systematic evaluation framework. Given that some studies evaluating the ability of generative AI for medical applications have deficiencies in their methodological design, standardized guidelines for their evaluation are also currently lacking. In response, our objective is to devise standardized assessment guidelines tailored for evaluating the performance of generative AI systems in medical contexts. To this end, we conducted a thorough literature review using the PubMed and Google Scholar databases, focusing on research that tests generative AI capabilities in medicine. Our multidisciplinary team, comprising experts in life sciences, clinical medicine, medical engineering, and generative AI users, conducted several discussion sessions and developed a checklist of 23 items. The checklist is designed to encompass the critical evaluation aspects of generative AI in medical applications comprehensively. This checklist, and the broader assessment framework it anchors, address several key dimensions, including question collection, querying methodologies, and assessment techniques. We aim to provide a holistic evaluation of AI systems. The checklist delineates a clear pathway from question gathering to result assessment, offering researchers guidance through potential challenges and pitfalls. Our framework furnishes a standardized, systematic approach for research involving the testing of generative AI's applicability in medicine. It enhances the quality of research reporting and aids in the evolution of generative AI in medicine and life sciences.

cs.HC↗
arXiv2023

PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction

Humans interact with objects all the time. Enabling a humanoid to learn human-object interaction (HOI) is a key step for future smart animation and intelligent robotics systems. However, recent progress in physics-based HOI requires carefully designed task-specific rewards, making the system unscalable and labor-intensive. This work focuses on dynamic HOI imitation: teaching humanoid dynamic interaction skills through imitating kinematic HOI demonstrations. It is quite challenging because of the complexity of the interaction between body parts and objects and the lack of dynamic HOI data. To handle the above issues, we present PhysHOI, the first physics-based whole-body HOI imitation approach without task-specific reward designs. Except for the kinematic HOI representations of humans and objects, we introduce the contact graph to model the contact relations between body parts and objects explicitly. A contact graph reward is also designed, which proved to be critical for precise HOI imitation. Based on the key designs, PhysHOI can imitate diverse HOI tasks simply yet effectively without prior knowledge. To make up for the lack of dynamic HOI scenarios in this area, we introduce the BallPlay dataset that contains eight whole-body basketball skills. We validate PhysHOI on diverse HOI tasks, including whole-body grasping and basketball skills.

cs.CV↗
arXiv2023

AnimateZero: Video Diffusion Models are Zero-Shot Image Animators

Large-scale text-to-video (T2V) diffusion models have great progress in recent years in terms of visual quality, motion and temporal consistency. However, the generation process is still a black box, where all attributes (e.g., appearance, motion) are learned and generated jointly without precise control ability other than rough text descriptions. Inspired by image animation which decouples the video as one specific appearance with the corresponding motion, we propose AnimateZero to unveil the pre-trained text-to-video diffusion model, i.e., AnimateDiff, and provide more precise appearance and motion control abilities for it. For appearance control, we borrow intermediate latents and their features from the text-to-image (T2I) generation for ensuring the generated first frame is equal to the given generated image. For temporal control, we replace the global temporal attention of the original T2V model with our proposed positional-corrected window attention to ensure other frames align with the first frame well. Empowered by the proposed methods, AnimateZero can successfully control the generating progress without further training. As a zero-shot image animator for given images, AnimateZero also enables multiple new applications, including interactive video generation and real image animation. The detailed experiments demonstrate the effectiveness of the proposed method in both T2V and related applications.

cs.CV↗
arXiv2023

Magnetic Order in A Quenched-High-Temperature-Phase of Cu-Doped MnBi

Permanent magnets are of great importance due to their vast applications. MnBi has been proposed to be a potential permanent magnet that can be widely used while past efforts have been focused on optimizing the ferromagnetic low-temperature phase of MnBi. Herein, we report a series of new materials, CuxMn1-xBi, crystallizing in a quenched high-temperature-phase (QHTP) MnBi-related structure. We synthesized single crystals of CuxMn1-xBi and found that they crystallize in an unreported trigonal structure (P -31c). Magnetic properties measurements imply high-temperature antiferromagnetic (AFM) ordering and low-temperature ferromagnetic or ferrimagnetic (FM/FiM) ordering. By analyzing the doping effect on crystal structure and magnetic properties, we established a magnetic phase diagram for Cu-doped MnBi and attributed the AFM and FM/FiM to two different atomic sites of Mn.

cond-mat.mtrl-sci↗
arXiv2023

SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning

In response to legislation mandating companies to honor the \textit{right to be forgotten} by erasing user data, it has become imperative to enable data removal in Vertical Federated Learning (VFL) where multiple parties provide private features for model training. In VFL, data removal, i.e., \textit{machine unlearning}, often requires removing specific features across all samples under privacy guarentee in federated learning. To address this challenge, we propose \methname, a novel Gradient Boosting Decision Tree (GBDT) framework that effectively enables both \textit{instance unlearning} and \textit{feature unlearning} without the need for retraining from scratch. Leveraging a robust GBDT structure, we enable effective data deletion while reducing degradation of model performance. Extensive experimental results on popular datasets demonstrate that our method achieves superior model utility and forgetfulness compared to \textit{state-of-the-art} methods. To our best knowledge, this is the first work that investigates machine unlearning in VFL scenarios.

cs.LG↗
arXiv2023

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

Despite the ability of existing large-scale text-to-image (T2I) models to generate high-quality images from detailed textual descriptions, they often lack the ability to precisely edit the generated or real images. In this paper, we propose a novel image editing method, DragonDiffusion, enabling Drag-style manipulation on Diffusion models. Specifically, we construct classifier guidance based on the strong correspondence of intermediate features in the diffusion model. It can transform the editing signals into gradients via feature correspondence loss to modify the intermediate representation of the diffusion model. Based on this guidance strategy, we also build a multi-scale guidance to consider both semantic and geometric alignment. Moreover, a cross-branch self-attention is added to maintain the consistency between the original image and the editing result. Our method, through an efficient design, achieves various editing modes for the generated or real images, such as object moving, object resizing, object appearance replacement, and content dragging. It is worth noting that all editing and content preservation signals come from the image itself, and the model does not require fine-tuning or additional modules. Our source code will be available at https://github.com/MC-E/DragonDiffusion.

cs.CV↗
arXiv2023

Multimodal Large Language Model for Visual Navigation

Recent efforts to enable visual navigation using large language models have mainly focused on developing complex prompt systems. These systems incorporate instructions, observations, and history into massive text prompts, which are then combined with pre-trained large language models to facilitate visual navigation. In contrast, our approach aims to fine-tune large language models for visual navigation without extensive prompt engineering. Our design involves a simple text prompt, current observations, and a history collector model that gathers information from previous observations as input. For output, our design provides a probability distribution of possible actions that the agent can take during navigation. We train our model using human demonstrations and collision signals from the Habitat-Matterport 3D Dataset (HM3D). Experimental results demonstrate that our method outperforms state-of-the-art behavior cloning methods and effectively reduces collision rates.

cs.CV↗
arXiv2023

Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning

Few-shot class-incremental learning (FSCIL) aims to build machine learning model that can continually learn new concepts from a few data samples, without forgetting knowledge of old classes. The challenges of FSCIL lies in the limited data of new classes, which not only lead to significant overfitting issues but also exacerbates the notorious catastrophic forgetting problems. As proved in early studies, building sample relationships is beneficial for learning from few-shot samples. In this paper, we promote the idea to the incremental scenario, and propose a Sample-to-Class (S2C) graph learning method for FSCIL. Specifically, we propose a Sample-level Graph Network (SGN) that focuses on analyzing sample relationships within a single session. This network helps aggregate similar samples, ultimately leading to the extraction of more refined class-level features. Then, we present a Class-level Graph Network (CGN) that establishes connections across class-level features of both new and old classes. This network plays a crucial role in linking the knowledge between different sessions and helps improve overall learning in the FSCIL scenario. Moreover, we design a multi-stage strategy for training S2C model, which mitigates the training challenges posed by limited data in the incremental process. The multi-stage training strategy is designed to build S2C graph from base to few-shot stages, and improve the capacity via an extra pseudo-incremental stage. Experiments on three popular benchmark datasets show that our method clearly outperforms the baselines and sets new state-of-the-art results in FSCIL.

cs.CV↗
arXiv2023

Shareable Driving Style Learning and Analysis with a Hierarchical Latent Model

Driving style is usually used to characterize driving behavior for a driver or a group of drivers. However, it remains unclear how one individual's driving style shares certain common grounds with other drivers. Our insight is that driving behavior is a sequence of responses to the weighted mixture of latent driving styles that are shareable within and between individuals. To this end, this paper develops a hierarchical latent model to learn the relationship between driving behavior and driving styles. We first propose a fragment-based approach to represent complex sequential driving behavior, allowing for sufficiently representing driving behavior in a low-dimension feature space. Then, we provide an analytical formulation for the interaction of driving behavior and shareable driving style with a hierarchical latent model by introducing the mechanism of Dirichlet allocation. Our developed model is finally validated and verified with 100 drivers in naturalistic driving settings with urban and highways. Experimental results reveal that individuals share driving styles within and between them. We also analyzed the influence of personalities (e.g., age, gender, and driving experience) on driving styles and found that a naturally aggressive driver would not always keep driving aggressively (i.e., could behave calmly sometimes) but with a higher proportion of aggressiveness than other types of drivers.

cs.RO↗
arXiv2023

Multilevel Perception Boundary-guided Network for Breast Lesion Segmentation in Ultrasound Images

Automatic segmentation of breast tumors from the ultrasound images is essential for the subsequent clinical diagnosis and treatment plan. Although the existing deep learning-based methods have achieved significant progress in automatic segmentation of breast tumor, their performance on tumors with similar intensity to the normal tissues is still not pleasant, especially for the tumor boundaries. To address this issue, we propose a PBNet composed by a multilevel global perception module (MGPM) and a boundary guided module (BGM) to segment breast tumors from ultrasound images. Specifically, in MGPM, the long-range spatial dependence between the voxels in a single level feature maps are modeled, and then the multilevel semantic information is fused to promote the recognition ability of the model for non-enhanced tumors. In BGM, the tumor boundaries are extracted from the high-level semantic maps using the dilation and erosion effects of max pooling, such boundaries are then used to guide the fusion of low and high-level features. Moreover, to improve the segmentation performance for tumor boundaries, a multi-level boundary-enhanced segmentation (BS) loss is proposed. The extensive comparison experiments on both publicly available dataset and in-house dataset demonstrate that the proposed PBNet outperforms the state-of-the-art methods in terms of both qualitative visualization results and quantitative evaluation metrics, with the Dice score, Jaccard coefficient, Specificity and HD95 improved by 0.70%, 1.1%, 0.1% and 2.5% respectively. In addition, the ablation experiments validate that the proposed MGPM is indeed beneficial for distinguishing the non-enhanced tumors and the BGM as well as the BS loss are also helpful for refining the segmentation contours of the tumor.

eess.IV↗
arXiv2023

Compatible Transformer for Irregularly Sampled Multivariate Time Series

To analyze multivariate time series, most previous methods assume regular subsampling of time series, where the interval between adjacent measurements and the number of samples remain unchanged. Practically, data collection systems could produce irregularly sampled time series due to sensor failures and interventions. However, existing methods designed for regularly sampled multivariate time series cannot directly handle irregularity owing to misalignment along both temporal and variate dimensions. To fill this gap, we propose Compatible Transformer (CoFormer), a transformer-based encoder to achieve comprehensive temporal-interaction feature learning for each individual sample in irregular multivariate time series. In CoFormer, we view each sample as a unique variate-time point and leverage intra-variate/inter-variate attentions to learn sample-wise temporal/interaction features based on intra-variate/inter-variate neighbors. With CoFormer as the core, we can analyze irregularly sampled multivariate time series for many downstream tasks, including classification and prediction. We conduct extensive experiments on 3 real-world datasets and validate that the proposed CoFormer significantly and consistently outperforms existing methods.

cs.LG↗
arXiv2023

Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling

Inspired by certain optimization solvers, the deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS). However, there still exist the following two issues: 1) In existing DUNs, most hyperparameters are usually content independent, which greatly limits their adaptability for different input contents. 2) In each iteration, a plain convolutional neural network is usually adopted, which weakens the perception of wider context prior and therefore depresses the expressive ability. In this paper, inspired by the traditional Proximal Gradient Descent (PGD) algorithm, a novel DUN for image compressed sensing (dubbed DUN-CSNet) is proposed to solve the above two issues. Specifically, for the first issue, a novel content adaptive gradient descent network is proposed, in which a well-designed step size generation sub-network is developed to dynamically allocate the corresponding step sizes for different textures of input image by generating a content-aware step size map, realizing a content-adaptive gradient updating. For the second issue, considering the fact that many similar patches exist in an image but have undergone a deformation, a novel deformation-invariant non-local proximal mapping network is developed, which can adaptively build the long-range dependencies between the nonlocal patches by deformation-invariant non-local modeling, leading to a wider perception on context priors. Extensive experiments manifest that the proposed DUN-CSNet outperforms existing state-of-the-art CS methods by large margins.

cs.CV↗
arXiv2023

Empirical Study of Zero-Shot NER with ChatGPT

Large language models (LLMs) exhibited powerful capability in various natural language processing tasks. This work focuses on exploring LLM performance on zero-shot information extraction, with a focus on the ChatGPT and named entity recognition (NER) task. Inspired by the remarkable reasoning capability of LLM on symbolic and arithmetic reasoning, we adapt the prevalent reasoning methods to NER and propose reasoning strategies tailored for NER. First, we explore a decomposed question-answering paradigm by breaking down the NER task into simpler subproblems by labels. Second, we propose syntactic augmentation to stimulate the model's intermediate thinking in two ways: syntactic prompting, which encourages the model to analyze the syntactic structure itself, and tool augmentation, which provides the model with the syntactic information generated by a parsing tool. Besides, we adapt self-consistency to NER by proposing a two-stage majority voting strategy, which first votes for the most consistent mentions, then the most consistent types. The proposed methods achieve remarkable improvements for zero-shot NER across seven benchmarks, including Chinese and English datasets, and on both domain-specific and general-domain scenarios. In addition, we present a comprehensive analysis of the error types with suggestions for optimization directions. We also verify the effectiveness of the proposed methods on the few-shot setting and other LLMs.

cs.CL↗
arXiv2023

TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Training

Text-guided image generation aimed to generate desired images conditioned on given texts, while text-guided image manipulation refers to semantically edit parts of a given image based on specified texts. For these two similar tasks, the key point is to ensure image fidelity as well as semantic consistency. Many previous approaches require complex multi-stage generation and adversarial training, while struggling to provide a unified framework for both tasks. In this work, we propose TextCLIP, a unified framework for text-guided image generation and manipulation without adversarial training. The proposed method accepts input from images or random noise corresponding to these two different tasks, and under the condition of the specific texts, a carefully designed mapping network that exploits the powerful generative capabilities of StyleGAN and the text image representation capabilities of Contrastive Language-Image Pre-training (CLIP) generates images of up to $1024\times1024$ resolution that can currently be generated. Extensive experiments on the Multi-modal CelebA-HQ dataset have demonstrated that our proposed method outperforms existing state-of-the-art methods, both on text-guided generation tasks and manipulation tasks.

cs.CV↗