arXiv subjects

Yangyang Li

Publications and source records attributed to Yangyang Li.

At least 55 records · Page 3Linked to original sources

arXiv2024

Masked Image Modeling Boosting Semi-Supervised Semantic Segmentation

In view of the fact that semi- and self-supervised learning share a fundamental principle, effectively modeling knowledge from unlabeled data, various semi-supervised semantic segmentation methods have integrated representative self-supervised learning paradigms for further regularization. However, the potential of the state-of-the-art generative self-supervised paradigm, masked image modeling, has been scarcely studied. This paradigm learns the knowledge through establishing connections between the masked and visible parts of masked image, during the pixel reconstruction process. By inheriting and extending this insight, we successfully leverage masked image modeling to boost semi-supervised semantic segmentation. Specifically, we introduce a novel class-wise masked image modeling that independently reconstructs different image regions according to their respective classes. In this way, the mask-induced connections are established within each class, mitigating the semantic confusion that arises from plainly reconstructing images in basic masked image modeling. To strengthen these intra-class connections, we further develop a feature aggregation strategy that minimizes the distances between features corresponding to the masked and visible parts within the same class. Additionally, in semantic space, we explore the application of masked image modeling to enhance regularization. Extensive experiments conducted on well-known benchmarks demonstrate that our approach achieves state-of-the-art performance. The code will be available at https://github.com/haoxt/S4MIM.

cs.CV↗

arXiv2024

Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media

Stance detection predicts attitudes towards targets in texts and has gained attention with the rise of social media. Traditional approaches include conventional machine learning, early deep neural networks, and pre-trained fine-tuning models. However, with the evolution of very large pre-trained language models (VLPLMs) like ChatGPT (GPT-3.5), traditional methods face deployment challenges. The parameter-free Chain-of-Thought (CoT) approach, not requiring backpropagation training, has emerged as a promising alternative. This paper examines CoT's effectiveness in stance detection tasks, demonstrating its superior accuracy and discussing associated challenges.

cs.CL↗

arXiv2024

Dual-Phase Accelerated Prompt Optimization

Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of high-quality prompt initialization and the identification of effective optimization directions, thus resulting in substantial optimization steps to obtain satisfactory performance. In this light, we aim to accelerate prompt optimization process to tackle the challenge of low convergence rate. We propose a dual-phase approach which starts with generating high-quality initial prompts by adopting a well-designed meta-instruction to delve into task-specific information, and iteratively optimize the prompts at the sentence level, leveraging previous tuning experience to expand prompt candidates and accept effective ones. Extensive experiments on eight datasets demonstrate the effectiveness of our proposed method, achieving a consistent accuracy gain over baselines with less than five optimization steps.

cs.CL↗

arXiv2024

Existence and regularity of min-max anisotropic minimal hypersurfaces

In any closed smooth Riemannian manifold of dimension at least three, we use the min-max construction to find anisotropic minimal hyper-surfaces with respect to elliptic integrands, with a singular set of codimension~$2$ vanishing Hausdorff measure. In particular, in a closed $3$-manifold, we obtain a smooth anisotropic minimal surface. The critical step is to obtain a uniform upper bound for density ratios in the anisotropic min-max construction. This confirms a conjecture by Allard [Invent. Math., 1983].

math.DG↗

arXiv2024

Discovery of a Metal-Poor Red Giant Star with the Highest Ultra-Lithium Enhancement

We present the discovery of 2MASS J05241392-0336543 (hereafter J0524-0336), a very metal-poor ([Fe/H]=-2.43 +- 0.16), highly r-process-enhanced ([Eu/Fe]= +1.34 +- 0.10) Milky Way halo field red giant star, with an ultra high Li abundance of A(Li)(3D,NLTE)= 6.15 +- 0.25 and [Li/Fe]= +7.64 +- 0.25, respectively. This makes J0524-0336 the most lithium-enhanced giant star discovered to date. We present a detailed analysis of the star's atmospheric stellar parameters and chemical abundance determinations. Additionally, we detect indications of infrared excess, as well as observe variable emission in the wings of the H_alpha absorption line across multiple epochs, indicative of a potential enhanced mass-loss event with possible outflows. Our analysis reveals that J0524-0336 lies either between the bump and the tip of the Red Giant Branch (RGB), or on the early-Asymptotic Giant Branch (e-AGB). We investigate the possible sources of lithium enrichment in J0524-0336, including both internal and external sources. Based on current models and on the observational evidence we have collected, our study shows that J0524-0336 may be undergoing the so-called lithium flash that is expected to occur in low-mass stars when they reach the RGB bump and/or the early-AGB.

astro-ph.SR↗

arXiv2024

Uncovering an Interfacial Band Resulting from Orbital Hybridization in Nickelate Heterostructures

The interaction of atomic orbitals at the interface of perovskite oxide heterostructures has been investigated for its profound impact on the band structures and electronic properties, giving rise to unique electronic states and a variety of tunable functionalities. In this study, we conducted an extensive investigation of the optical and electronic properties of epitaxial NdNiO3 thin films grown on a series of single crystal substrates. Unlike films synthesized on other substrates, NdNiO3 on SrTiO3 (NNO/STO) gives rise to a unique band structure which features an additional unoccupied band situated above the Fermi level. Our comprehensive investigation, which incorporated a wide array of experimental techniques and density functional theory calculations, revealed that the emergence of the interfacial band structure is primarily driven by the orbital hybridization between Ti 3d orbitals of the STO substrate and O 2p orbitals of the NNO thin film. Furthermore, exciton peaks have been detected in the optical spectra of the NNO/STO film, attributable to the pronounced electron-electron (e-e) and electron-hole (e-h) interactions propagating from the STO substrate into the NNO film. These findings underscore the substantial influence of interfacial orbital hybridization on the electronic structure of oxide thin-films, thereby offering key insights into tuning their interfacial properties.

cond-mat.mtrl-sci↗

arXiv2023

LICO: Explainable Models with Language-Image Consistency

Interpreting the decisions of deep learning models has been actively studied since the explosion of deep neural networks. One of the most convincing interpretation approaches is salience-based visual interpretation, such as Grad-CAM, where the generation of attention maps depends merely on categorical labels. Although existing interpretation methods can provide explainable decision clues, they often yield partial correspondence between image and saliency maps due to the limited discriminative information from one-hot labels. This paper develops a Language-Image COnsistency model for explainable image classification, termed LICO, by correlating learnable linguistic prompts with corresponding visual features in a coarse-to-fine manner. Specifically, we first establish a coarse global manifold structure alignment by minimizing the distance between the distributions of image and language features. We then achieve fine-grained saliency maps by applying optimal transport (OT) theory to assign local feature maps with class-specific prompts. Extensive experimental results on eight benchmark datasets demonstrate that the proposed LICO achieves a significant improvement in generating more explainable attention maps in conjunction with existing interpretation methods such as Grad-CAM. Remarkably, LICO improves the classification performance of existing models without introducing any computational overhead during inference. Source code is made available at https://github.com/ymLeiFDU/LICO.

cs.CV↗

arXiv2023

Watch out Venomous Snake Species: A Solution to SnakeCLEF2023

The SnakeCLEF2023 competition aims to the development of advanced algorithms for snake species identification through the analysis of images and accompanying metadata. This paper presents a method leveraging utilization of both images and metadata. Modern CNN models and strong data augmentation are utilized to learn better representation of images. To relieve the challenge of long-tailed distribution, seesaw loss is utilized in our method. We also design a light model to calculate prior probabilities using metadata features extracted from CLIP in post processing stage. Besides, we attach more importance to venomous species by assigning venomous species labels to some examples that model is uncertain about. Our method achieves 91.31% score of the final metric combined of F1 and other metrics on private leaderboard, which is the 1st place among the participators. The code is available at https://github.com/xiaoxsparraw/CLEF2023.

cs.CV↗

arXiv2023

Focusing on Relevant Responses for Multi-modal Rumor Detection

In the absence of an authoritative statement about a rumor, people may expose the truth behind such rumor through their responses on social media. Most rumor detection methods aggregate the information of all the responses and have made great progress. However, due to the different backgrounds of users, the responses have different relevance for discovering th suspicious points hidden in a rumor claim. The methods that focus on all the responding tweets would dilute the effect of the critical ones. Moreover, for a multi-modal rumor claim, the focus of a user may be on several words in the text or an object in the image, so the different modalities should be considered to select the relevant responses and verify the claim. In this paper, we propose a novel multi-modal rumor detection model, termed Focal Reasoning Model (FoRM), to filter out the irrelevant responses and further conduct fine-grained reasoning with the multi-modal claim and corresponding responses. Concretely, there are two main components in our FoRM: the coarse-grained selection and the fine-grained reasoning. The coarse-grained selection component leverages the post-level features of the responses to verify the claim and learns a relevant score of each response. Based on the relevant scores, the most relevant responses are reserved as the critical ones to the further reasoning. In the fine-grained reasoning component, we design a relation attention module to explore the fine-grained relations, i.e., token-to-token and token-to-object relations, between the reserved responses and the multi-modal claim for finding out the valuable clues. Extensive experiments have been conducted on two real-world datasets, and the results demonstrate that our proposed model outperforms all the baselines.

cs.SI↗

arXiv2023

DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing

The knowledge distillation uses a high-performance teacher network to guide the student network. However, the performance gap between the teacher and student networks can affect the student's training. This paper proposes a novel knowledge distillation algorithm based on dynamic entropy correction to reduce the gap by adjusting the student instead of the teacher. Firstly, the effect of changing the output entropy (short for output information entropy) in the student on the distillation loss is analyzed in theory. This paper shows that correcting the output entropy can reduce the gap. Then, a knowledge distillation algorithm based on dynamic entropy correction is created, which can correct the output entropy in real-time with an entropy controller updated dynamically by the distillation loss. The proposed algorithm is validated on the CIFAR100 and ImageNet. The comparison with various state-of-the-art distillation algorithms shows impressive results, especially in the experiment on the CIFAR100 regarding teacher-student pair resnet32x4-resnet8x4. The proposed algorithm raises 2.64 points over the traditional distillation algorithm and 0.87 points over the state-of-the-art algorithm CRD in classification accuracy, demonstrating its effectiveness and efficiency.

cs.CV↗

arXiv2023

FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot Detection

Social bot detection is of paramount importance to the resilience and security of online social platforms. The state-of-the-art detection models are siloed and have largely overlooked a variety of data characteristics from multiple cross-lingual platforms. Meanwhile, the heterogeneity of data distribution and model architecture makes it intricate to devise an efficient cross-platform and cross-model detection framework. In this paper, we propose FedACK, a new federated adversarial contrastive knowledge distillation framework for social bot detection. We devise a GAN-based federated knowledge distillation mechanism for efficiently transferring knowledge of data distribution among clients. In particular, a global generator is used to extract the knowledge of global data distribution and distill it into each client's local model. We leverage local discriminator to enable customized model design and use local generator for data enhancement with hard-to-decide samples. Local training is conducted as multi-stage adversarial and contrastive learning to enable consistent feature spaces among clients and to constrain the optimization direction of local models, reducing the divergences between local and global models. Experiments demonstrate that FedACK outperforms the state-of-the-art approaches in terms of accuracy, communication efficiency, and feature space consistency.

cs.LG↗

arXiv2023

LOTUS: A (non-)LTE Optimization Tool for Uniform derivation of Stellar atmospheric parameters

Precise fundamental atmospheric stellar parameters and abundance determination of individual elements in stars are important for all stellar population studies. Non-Local Thermodynamic Equilibrium (Non-LTE; hereafter NLTE) models are often important for such high precision, however, can be computationally complex and expensive, which renders the models less utilized in spectroscopic analyses. To alleviate the computational burden of such models, we developed a robust 1D, LTE and NLTE fundamental atmospheric stellar parameter derivation tool, $\texttt{LOTUS}$, to determine the effective temperature $T_{\mathrm{eff}}$, surface gravity $\log g$, metallicity $\mbox{[Fe/H]}$ and microturbulent velocity $v_{\mathrm{mic}}$ for FGK type stars, from equivalent width (EW) measurements of Fe I and Fe II lines. We utilize a generalized curve of growth method to take into account the EW dependencies of each Fe I and Fe II line on the corresponding atmospheric stellar parameters. A global differential evolution optimization algorithm is then used to derive the optimized fundamental parameters. Additionally, $\texttt{LOTUS}$ can determine precise uncertainties for each stellar parameter using a Markov Chain Monte Carlo (MCMC) algorithm. We test and apply $\texttt{LOTUS}$ on a sample of benchmark stars, as well as stars with available asteroseismic surface gravities from the K2 survey, and metal-poor stars from $R$-process Alliance (RPA) survey. We find very good agreement between our NLTE-derived parameters in $\texttt{LOTUS}$ to non-spectroscopic values within $T_{\mathrm{eff}}=\pm 30$ K and $\log g=\pm 0.10$ dex for benchmark stars. We provide open access of our code, as well as of the interpolated pre-computed NLTE EW grids available on Github, and documentation with working examples on Readthedocs.

astro-ph.SR↗

arXiv2023

CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation

The goal of image ordinal estimation is to estimate the ordinal label of a given image with a convolutional neural network. Existing methods are mainly based on ordinal regression and particularly focus on modeling the ordinal mapping from the feature representation of the input to the ordinal label space. However, the manifold of the resultant feature representations does not maintain the intrinsic ordinal relations of interest, which hinders the effectiveness of the image ordinal estimation. Therefore, this paper proposes learning intrinsic Consistent Ordinal REpresentations (CORE) from ordinal relations residing in groundtruth labels while encouraging the feature representations to embody the ordinal low-dimensional manifold. First, we develop an ordinal totally ordered set (toset) distribution (OTD), which can (i) model the label embeddings to inherit ordinal information and measure distances between ordered labels of samples in a neighborhood, and (ii) model the feature embeddings to infer numerical magnitude with unknown ordinal information among the features of different samples. Second, through OTD, we convert the feature representations and labels into the same embedding space for better alignment, and then compute the Kullback Leibler (KL) divergence between the ordinal labels and feature representations to endow the latent space with consistent ordinal relations. Third, we optimize the KL divergence through ordinal prototype-constrained convex programming with dual decomposition; our theoretical analysis shows that we can obtain the optimal solutions via gradient backpropagation. Extensive experimental results demonstrate that the proposed CORE can accurately construct an ordinal latent space and significantly enhance existing deep ordinal regression methods to achieve better results.

cs.CV↗

arXiv2022

RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search

Social bots are referred to as the automated accounts on social networks that make attempts to behave like human. While Graph Neural Networks (GNNs) has been massively applied to the field of social bot detection, a huge amount of domain expertise and prior knowledge is heavily engaged in the state-of-the art approaches to design a dedicated neural network architecture for a specific classification task. Involving oversized nodes and network layers in the model design, however, usually causes the over-smoothing problem and the lack of embedding discrimination. In this paper, we propose RoSGAS, a novel Reinforced and Self-supervised GNN Architecture Search framework to adaptively pinpoint the most suitable multi-hop neighborhood and the number of layers in the GNN architecture. More specifically, we consider the social bot detection problem as a user-centric subgraph embedding and classification task. We exploit heterogeneous information network to present the user connectivity by leveraging account metadata, relationships, behavioral features and content features. RoSGAS uses a multi-agent deep reinforcement learning (RL) mechanism for navigating the search of optimal neighborhood and network layers to learn individually the subgraph embedding for each target user. A nearest neighbor mechanism is developed for accelerating the RL training process, and RoSGAS can learn more discriminative subgraph embedding with the aid of self-supervised learning. Experiments on 5 Twitter datasets show that RoSGAS outperforms the state-of-the-art approaches in terms of accuracy, training efficiency and stability, and has better generalization when handling unseen samples.

cs.SI↗

arXiv2022

Deep reinforcement learning guided graph neural networks for brain network analysis

Modern neuroimaging techniques, such as diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI), enable us to model the human brain as a brain network or connectome. Capturing brain networks' structural information and hierarchical patterns is essential for understanding brain functions and disease states. Recently, the promising network representation learning capability of graph neural networks (GNNs) has prompted many GNN-based methods for brain network analysis to be proposed. Specifically, these methods apply feature aggregation and global pooling to convert brain network instances into meaningful low-dimensional representations used for downstream brain network analysis tasks. However, existing GNN-based methods often neglect that brain networks of different subjects may require various aggregation iterations and use GNN with a fixed number of layers to learn all brain networks. Therefore, how to fully release the potential of GNNs to promote brain network analysis is still non-trivial. To solve this problem, we propose a novel brain network representation framework, namely BN-GNN, which searches for the optimal GNN architecture for each brain network. Concretely, BN-GNN employs deep reinforcement learning (DRL) to train a meta-policy to automatically determine the optimal number of feature aggregations (reflected in the number of GNN layers) required for a given brain network. Extensive experiments on eight real-world brain network datasets demonstrate that our proposed BN-GNN improves the performance of traditional GNNs on different brain network analysis tasks.

cs.LG↗

arXiv2022

Minimal hypersurfaces for generic metrics in dimension 8

We show that in an $8$-dimensional closed Riemmanian manifold with $C^\infty$-generic metrics, every minimal hypersurface is smooth and nondegenerate. This confirms a full generic regularity conjecture of minimal hypersurfaces in dimension eight. This also enables us to generalize many generic geometric properties of (Almgren-Pitts) min-max minimal hypersurfaces, previously only known in low dimensions, to dimension eight.

math.DG↗

arXiv2022

Equivariant $3$-manifolds with positive scalar curvature

In this paper, for any compact Lie group $G$, we show that the space of $G$-invariant Riemannian metrics with positive scalar curvature (PSC) on any closed three-manifold is either empty or contractible. In particular, we prove the generalized Smale conjecture for spherical three-orbifolds. Moreover, for connected $G$, we make a classification of all PSC $G$-invariant three-manifolds.

math.DG↗

arXiv2022

Location-Free Camouflage Generation Network

Camouflage is a common visual phenomenon, which refers to hiding the foreground objects into the background images, making them briefly invisible to the human eye. Previous work has typically been implemented by an iterative optimization process. However, these methods struggle in 1) efficiently generating camouflage images using foreground and background with arbitrary structure; 2) camouflaging foreground objects to regions with multiple appearances (e.g. the junction of the vegetation and the mountains), which limit their practical application. To address these problems, this paper proposes a novel Location-free Camouflage Generation Network (LCG-Net) that fuse high-level features of foreground and background image, and generate result by one inference. Specifically, a Position-aligned Structure Fusion (PSF) module is devised to guide structure feature fusion based on the point-to-point structure similarity of foreground and background, and introduce local appearance features point-by-point. To retain the necessary identifiable features, a new immerse loss is adopted under our pipeline, while a background patch appearance loss is utilized to ensure that the hidden objects look continuous and natural at regions with multiple appearances. Experiments show that our method has results as satisfactory as state-of-the-art in the single-appearance regions and are less likely to be completely invisible, but far exceed the quality of the state-of-the-art in the multi-appearance regions. Moreover, our method is hundreds of times faster than previous methods. Benefitting from the unique advantages of our method, we provide some downstream applications for camouflage generation, which show its potential. The related code and dataset will be released at https://github.com/Tale17/LCG-Net.

cs.CV↗