arXiv subjects

Xiao Yang

Publications and source records attributed to Xiao Yang.

At least 181 records · Page 10Linked to original sources

arXiv2024

Common Diffusion Noise Schedules and Sample Steps are Flawed

We discover that common diffusion noise schedules do not enforce the last timestep to have zero signal-to-noise ratio (SNR), and some implementations of diffusion samplers do not start from the last timestep. Such designs are flawed and do not reflect the fact that the model is given pure Gaussian noise at inference, creating a discrepancy between training and inference. We show that the flawed design causes real problems in existing implementations. In Stable Diffusion, it severely limits the model to only generate images with medium brightness and prevents it from generating very bright and dark samples. We propose a few simple fixes: (1) rescale the noise schedule to enforce zero terminal SNR; (2) train the model with v prediction; (3) change the sampler to always start from the last timestep; (4) rescale classifier-free guidance to prevent over-exposure. These simple changes ensure the diffusion process is congruent between training and inference and allow the model to generate samples more faithful to the original data distribution.

cs.CV↗

arXiv2023

On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications

The advent of large language models (LLMs) has heightened interest in their potential for multimodal applications that integrate language and vision. This paper explores the capabilities of GPT-4V in the realms of geography, environmental science, agriculture, and urban planning by evaluating its performance across a variety of tasks. Data sources comprise satellite imagery, aerial photos, ground-level images, field images, and public datasets. The model is evaluated on a series of tasks including geo-localization, textual data extraction from maps, remote sensing image classification, visual question answering, crop type identification, disease/pest/weed recognition, chicken behavior analysis, agricultural object counting, urban planning knowledge question answering, and plan generation. The results indicate the potential of GPT-4V in geo-localization, land cover classification, visual question answering, and basic image understanding. However, there are limitations in several tasks requiring fine-grained recognition and precise counting. While zero-shot learning shows promise, performance varies across problem domains and image complexities. The work provides novel insights into GPT-4V's capabilities and limitations for real-world geospatial, environmental, agricultural, and urban planning challenges. Further research should focus on augmenting the model's knowledge and reasoning for specialized domains through expanded training. Overall, the analysis demonstrates foundational multimodal intelligence, highlighting the potential of multimodal foundation models (FMs) to advance interdisciplinary applications at the nexus of computer vision and language.

cs.CV↗

arXiv2023

YOLO-OB: An improved anchor-free real-time multiscale colon polyp detector in colonoscopy

Colon cancer is expected to become the second leading cause of cancer death in the United States in 2023. Although colonoscopy is one of the most effective methods for early prevention of colon cancer, up to 30% of polyps may be missed by endoscopists, thereby increasing patients' risk of developing colon cancer. Though deep neural networks have been proven to be an effective means of enhancing the detection rate of polyps. However, the variation of polyp size brings the following problems: (1) it is difficult to design an efficient and sufficient multi-scale feature fusion structure; (2) matching polyps of different sizes with fixed-size anchor boxes is a hard challenge. These problems reduce the performance of polyp detection and also lower the model's training and detection efficiency. To address these challenges, this paper proposes a new model called YOLO-OB. Specifically, we developed a bidirectional multiscale feature fusion structure, BiSPFPN, which could enhance the feature fusion capability across different depths of a CNN. We employed the ObjectBox detection head, which used a center-based anchor-free box regression strategy that could detect polyps of different sizes on feature maps of any scale. Experiments on the public dataset SUN and the self-collected colon polyp dataset Union demonstrated that the proposed model significantly improved various performance metrics of polyp detection, especially the recall rate. Compared to the state-of-the-art results on the public dataset SUN, the proposed method achieved a 6.73% increase on recall rate from 91.5% to 98.23%. Furthermore, our YOLO-OB was able to achieve real-time polyp detection at a speed of 39 frames per second using a RTX3090 graphics card. The implementation of this paper can be found here: https://github.com/seanyan62/YOLO-OB.

cs.CV↗

arXiv2023

Observations of Magnetic Helicity Proxies in Solar Photosphere: Helicity with Solar Cycles

Observations of magnetic helicity transportation through the solar photosphere reflect the interaction of turbulent plasma movements and magnetic fields in the solar dynamo process. In this chapter, we have reviewed the research process of magnetic helicity inferred from the observed solar magnetic fields in the photosphere and also the solar morphological configurations with solar cycles. After introducing some achievements in the study of magnetic helicity, some key points would like to be summarized. The magnetic (current) helicity in the solar surface layer presents a statistical distribution similar to that of the sunspot butterfly diagram, but its maximum value is delayed from the extreme value of the sunspot butterfly diagram and corresponds in the phase with the statistical eruption of solar flares. During the spatial transport of magnetic (current) helicity from the interior of the sun into the interplanetary space at the time-space scale of the solar cycle, it shows the statistical distribution and the fluctuation with the hemispheric sign rule. These show that the current helicity and magnetic helicity transport calculation methods are complementary to each other. We also notice that the study of the inherent relationship between magnetic helicity and the solar cycle still depends on the observed accuracy of the solar magnetic field.

astro-ph.SR↗

arXiv2023

On Evaluating Adversarial Robustness of Large Vision-Language Models

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT. Nonetheless, multimodal generation exacerbates safety concerns, since adversaries may successfully evade the entire system by subtly manipulating the most vulnerable modality (e.g., vision). To this end, we propose evaluating the robustness of open-source large VLMs in the most realistic and high-risk setting, where adversaries have only black-box system access and seek to deceive the model into returning the targeted responses. In particular, we first craft targeted adversarial examples against pretrained models such as CLIP and BLIP, and then transfer these adversarial examples to other VLMs such as MiniGPT-4, LLaVA, UniDiffuser, BLIP-2, and Img2Prompt. In addition, we observe that black-box queries on these VLMs can further improve the effectiveness of targeted evasion, resulting in a surprisingly high success rate for generating targeted responses. Our findings provide a quantitative understanding regarding the adversarial vulnerability of large VLMs and call for a more thorough examination of their potential security flaws before deployment in practice. Code is at https://github.com/yunqing-me/AttackVLM.

cs.CV↗

arXiv2023

Leveraging Large Language Model for Automatic Evolving of Industrial Data-Centric R&D Cycle

In the wake of relentless digital transformation, data-driven solutions are emerging as powerful tools to address multifarious industrial tasks such as forecasting, anomaly detection, planning, and even complex decision-making. Although data-centric R&D has been pivotal in harnessing these solutions, it often comes with significant costs in terms of human, computational, and time resources. This paper delves into the potential of large language models (LLMs) to expedite the evolution cycle of data-centric R&D. Assessing the foundational elements of data-centric R&D, including heterogeneous task-related data, multi-facet domain knowledge, and diverse computing-functional tools, we explore how well LLMs can understand domain-specific requirements, generate professional ideas, utilize domain-specific tools to conduct experiments, interpret results, and incorporate knowledge from past endeavors to tackle new challenges. We take quantitative investment research as a typical example of industrial data-centric R&D scenario and verified our proposed framework upon our full-stack open-sourced quantitative research platform Qlib and obtained promising results which shed light on our vision of automatic evolving of industrial data-centric R&D cycle.

cs.AI↗

arXiv2023

A Recipe for Watermarking Diffusion Models

Diffusion models (DMs) have demonstrated advantageous potential on generative tasks. Widespread interest exists in incorporating DMs into downstream applications, such as producing or editing photorealistic images. However, practical deployment and unprecedented power of DMs raise legal issues, including copyright protection and monitoring of generated content. In this regard, watermarking has been a proven solution for copyright protection and content monitoring, but it is underexplored in the DMs literature. Specifically, DMs generate samples from longer tracks and may have newly designed multimodal structures, necessitating the modification of conventional watermarking pipelines. To this end, we conduct comprehensive analyses and derive a recipe for efficiently watermarking state-of-the-art DMs (e.g., Stable Diffusion), via training from scratch or finetuning. Our recipe is straightforward but involves empirically ablated implementation details, providing a foundation for future research on watermarking DMs. The code is available at https://github.com/yunqing-me/WatermarkDM.

cs.CV↗

arXiv2023

How Robust is Google's Bard to Adversarial Image Attacks?

Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustness problem of vision models, MLLMs can have more severe safety and security risks by introducing the vision inputs. In this work, we study the adversarial robustness of Google's Bard, a competitive chatbot to ChatGPT that released its multimodal capability recently, to better understand the vulnerabilities of commercial MLLMs. By attacking white-box surrogate vision encoders or MLLMs, the generated adversarial examples can mislead Bard to output wrong image descriptions with a 22% success rate based solely on the transferability. We show that the adversarial examples can also attack other MLLMs, e.g., a 26% attack success rate against Bing Chat and a 86% attack success rate against ERNIE bot. Moreover, we identify two defense mechanisms of Bard, including face detection and toxicity detection of images. We design corresponding attacks to evade these defenses, demonstrating that the current defenses of Bard are also vulnerable. We hope this work can deepen our understanding on the robustness of MLLMs and facilitate future research on defenses. Our code is available at https://github.com/thu-ml/Attack-Bard. Update: GPT-4V is available at October 2023. We further evaluate its robustness under the same set of adversarial examples, achieving a 45% attack success rate.

cs.CV↗

arXiv2023

An unprecedented synergy of high-temperature tensile strength and ductility in a NiCoCrAlTi high-entropy alloy

The present work reported a novel L12-strengthening NiCoCrAlTi high entropy alloy (HEA) with an outstanding synergy of tensile strength and ductility at both ambient and high temperatures. Transmission electron microscopy (TEM) characterization revealed a high density of rod-like and spheroidal L12 precipitates distributing in the micro/nanograins and non-recrystallized regions in the annealed specimens. The tremendously high yield stress, ultimate tensile stress (UTS), and ductility of the HEA at 600 C were ~1060 MPa, 1271 MPa, and 25%, respectively, which were significantly superior to most reported HEAs and Co- and Ni-based superalloys to date. Systematic TEM analysis unveiled that the cooperation among L12 precipitation, extensive stacking faults (SFs), deformation twins (DTs), immobile Lomer-Cottrell (L-C) locks formed from interactions between SFs and SFs/DTs, hierarchical SFs/DTs networks, as well as hetero-deformation-induced strengthening dominated the plastic deformation at 600 C. Such a unique deformation mechanism enabled extremely high tensile strength and sustained ductility of the HEA at a high temperature.

cond-mat.mtrl-sci↗

arXiv2023

Knowledge-Driven Multi-Agent Reinforcement Learning for Computation Offloading in Cybertwin-Enabled Internet of Vehicles

By offloading computation-intensive tasks of vehicles to roadside units (RSUs), mobile edge computing (MEC) in the Internet of Vehicles (IoV) can relieve the onboard computation burden. However, existing model-based task offloading methods suffer from heavy computational complexity with the increase of vehicles and data-driven methods lack interpretability. To address these challenges, in this paper, we propose a knowledge-driven multi-agent reinforcement learning (KMARL) approach to reduce the latency of task offloading in cybertwin-enabled IoV. Specifically, in the considered scenario, the cybertwin serves as a communication agent for each vehicle to exchange information and make offloading decisions in the virtual space. To reduce the latency of task offloading, a KMARL approach is proposed to select the optimal offloading option for each vehicle, where graph neural networks are employed by leveraging domain knowledge concerning graph-structure communication topology and permutation invariance into neural networks. Numerical results show that our proposed KMARL yields higher rewards and demonstrates improved scalability compared with other methods, benefitting from the integration of domain knowledge.

cs.LG↗

arXiv2023

Transition metal single-atom anchored on MoSi2N4 monolayer as highly efficient electrocatalyst for hydrogen evolution reaction

Single-atom catalysts are considered as a promising method for efficient energy conversion, owing to their advantages of high atom utilization and low catalyst cost. However, finding a stable two-dimensional structure and high hydrogen evolution reaction (HER) performance is a current research hotspot. Herein, based on the first-principles calculations, we identify the HER properties of six catalysts (TM@MoSi2N4, TM = Sc, Ti, V, Fe, Co, and Ni) comprising transition metal atoms anchored on MoSi2N4 monolayer. The results show that the spin-polarized states appear around the Fermi level after anchoring TM atoms. Therefore, the energy level of the first available unoccupied state for accommodating hydrogen drops, regulating the bonding strength of hydrogen. Thus, the single transition metal atom activates the active site of the MoSi2N4 inert base plane, becoming a quite suitable site for the HER. Based on ΔGH*, the exchange current density and volcano diagram of the corresponding catalytic system were also calculated. Among them, V@MoSi2N4 (ΔGH* = -0.07 eV) and Ni@MoSi2N4 (ΔGH* = 0.06 eV) systems show efficient the HER property. Our study confirms that the transition metal atom anchoring is an effective means to improve the performance of electrocatalysis, and TM@MoSi2N4 has practical application potential as a high efficiency HER electrocatalyst.

cond-mat.mtrl-sci↗

arXiv2023

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

This work focuses on the 3D reconstruction of non-rigid objects based on monocular RGB video sequences. Concretely, we aim at building high-fidelity models for generic object categories and casually captured scenes. To this end, we do not assume known root poses of objects, and do not utilize category-specific templates or dense pose priors. The key idea of our method, Root Pose Decomposition (RPD), is to maintain a per-frame root pose transformation, meanwhile building a dense field with local transformations to rectify the root pose. The optimization of local transformations is performed by point registration to the canonical space. We also adapt RPD to multi-object scenarios with object occlusions and individual differences. As a result, RPD allows non-rigid 3D reconstruction for complicated scenarios containing objects with large deformations, complex motion patterns, occlusions, and scale diversities of different individuals. Such a pipeline potentially scales to diverse sets of objects in the wild. We experimentally show that RPD surpasses state-of-the-art methods on the challenging DAVIS, OVIS, and AMA datasets.

cs.CV↗

arXiv2023

Change ratios of magnetic helicity and magnetic free energy during major solar flares

Magnetic helicity is an important concept in solar physics, with a number of theoretical statements pointing out the important role of magnetic helicity in solar flares and coronal mass ejections (CMEs). Here we construct a sample of 47 solar flares, which contains 18 no-CME-associated confined flares and 29 CME-associated eruptive flares. We calculate the change ratios of magnetic helicity and magnetic free energy before and after these 47 flares. Our calculations show that the change ratios of magnetic helicity and magnetic free energy show distinct different distributions in confined flares and eruptive flares. The median value of the change ratios of magnetic helicity in confined flares is $-0.8$%, while this number is $-14.5$% for eruptive flares. For the magnetic free energy, the median value of the change ratios is $-4.3$% for confined flares, whereas this number is $-14.6$% for eruptive flares. This statistical result, using observational data, is well consistent with the theoretical understandings that magnetic helicity is approximately conserved in the magnetic reconnection, as shown by confined flares, and the CMEs take away magnetic helicity from the corona, as shown by eruptive flares.

astro-ph.SR↗

arXiv2023

AdvFAS: A robust face anti-spoofing framework against adversarial examples

Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the most state-of-the-art methods to defend against adversarial examples remains elusive. While several adversarial defense strategies have been proposed, they typically suffer from constrained practicability due to inevitable trade-offs between universality, effectiveness, and efficiency. To overcome these challenges, we thoroughly delve into the coupled relationship between adversarial detection and face anti-spoofing. Based on this, we propose a robust face anti-spoofing framework, namely AdvFAS, that leverages two coupled scores to accurately distinguish between correctly detected and wrongly detected face images. Extensive experiments demonstrate the effectiveness of our framework in a variety of settings, including different attacks, datasets, and backbones, meanwhile enjoying high accuracy on clean examples. Moreover, we successfully apply the proposed method to detect real-world adversarial examples.

cs.CV↗

arXiv2023

Improving Opinion-based Question Answering Systems Through Label Error Detection and Overwrite

Label error is a ubiquitous problem in annotated data. Large amounts of label error substantially degrades the quality of deep learning models. Existing methods to tackle the label error problem largely focus on the classification task, and either rely on task specific architecture or require non-trivial additional computations, which is undesirable or even unattainable for industry usage. In this paper, we propose LEDO: a model-agnostic and computationally efficient framework for Label Error Detection and Overwrite. LEDO is based on Monte Carlo Dropout combined with uncertainty metrics, and can be easily generalized to multiple tasks and data sets. Applying LEDO to an industry opinion-based question answering system demonstrates it is effective at improving accuracy in all the core models. Specifically, LEDO brings 1.1% MRR gain for the retrieval model, 1.5% PR AUC improvement for the machine reading comprehension model, and 0.9% rise in the Average Precision for the ranker, on top of the strong baselines with a large-scale social media dataset. Importantly, LEDO is computationally efficient compared to methods that require loss function change, and cost-effective as the resulting data can be used in the same continuous training pipeline for production. Further analysis shows that these gains come from an improved decision boundary after cleaning the label errors existed in the training data.

cs.CL↗

arXiv2023

Unifying gradient regularization for Heterogeneous Graph Neural Networks

Heterogeneous Graph Neural Networks (HGNNs) are a class of powerful deep learning methods widely used to learn representations of heterogeneous graphs. Despite the fast development of HGNNs, they still face some challenges such as over-smoothing, and non-robustness. Previous studies have shown that these problems can be reduced by using gradient regularization methods. However, the existing gradient regularization methods focus on either graph topology or node features. There is no universal approach to integrate these features, which severely affects the efficiency of regularization. In addition, the inclusion of gradient regularization into HGNNs sometimes leads to some problems, such as an unstable training process, increased complexity and insufficient coverage regularized information. Furthermore, there is still short of a complete theoretical analysis of the effects of gradient regularization on HGNNs. In this paper, we propose a novel gradient regularization method called Grug, which iteratively applies regularization to the gradients generated by both propagated messages and the node features during the message-passing process. Grug provides a unified framework integrating graph topology and node features, based on which we conduct a detailed theoretical analysis of their effectiveness. Specifically, the theoretical analyses elaborate the advantages of Grug: 1) Decreasing sample variance during the training process (Stability); 2) Enhancing the generalization of the model (Universality); 3) Reducing the complexity of the model (Simplicity); 4) Improving the integrity and diversity of graph information utilization (Diversity). As a result, Grug has the potential to surpass the theoretical upper bounds set by DropMessage (AAAI-23 Distinguished Papers). In addition, we evaluate Grug on five public real-world datasets with two downstream tasks...

cs.LG↗

arXiv2023

Built-in electric field and strain tunable valley-related multiple topological phase transitions in VSiXN$_4$ (X= C, Si, Ge, Sn, Pb) monolayers

The valley-related multiple topological phase transitions attracted significant attention due to their providing significant opportunities for fundamental research and practical applications. However, unfortunately, to date there is no real material that can realize valley-related multiple topological phase transitions. Here, through first-principles calculations and model analysis, we investigate the structural, magnetic, electronic, and topological properties of VSiXN$_4$ (X = C, Si, Ge, Sn, Pb) monolayers. VSiXN$_4$ monolayers are stable and intrinsically ferrovalley materials. Intriguingly, we found that the built-in electric field and strain can induce valley-related multiple topological phase transitions in the materials from valley semiconductor to valley-half-semimetal, to valley quantum anomalous Hall insulator, to valley-half-semimetal, and to valley semiconductor (or to valley-metal). The nature of topological phase transition is the built-in electric field and strain induce band inversion between the d$_{xy}$/d$_{x2-y2}$ and d$_{z2}$ at obritals at K and K' valleys. Our findings not only reveal the mechanism of multiple topological phase transitions, but also provides an ideal platform for the multi-field manipulating the spin, valley, and topological physics. It will open new perspectives for spintronic, valleytronic, and topological nanoelectronic applications based on these materials.

cond-mat.mes-hall↗

arXiv2023

SAM for Poultry Science

In recent years, the agricultural industry has witnessed significant advancements in artificial intelligence (AI), particularly with the development of large-scale foundational models. Among these foundation models, the Segment Anything Model (SAM), introduced by Meta AI Research, stands out as a groundbreaking solution for object segmentation tasks. While SAM has shown success in various agricultural applications, its potential in the poultry industry, specifically in the context of cage-free hens, remains relatively unexplored. This study aims to assess the zero-shot segmentation performance of SAM on representative chicken segmentation tasks, including part-based segmentation and the use of infrared thermal images, and to explore chicken-tracking tasks by using SAM as a segmentation tool. The results demonstrate SAM's superior performance compared to SegFormer and SETR in both whole and part-based chicken segmentation. SAM-based object tracking also provides valuable data on the behavior and movement patterns of broiler birds. The findings of this study contribute to a better understanding of SAM's potential in poultry science and lay the foundation for future advancements in chicken segmentation and tracking.

cs.CV↗