arXiv subjects

Yifan Sun

Publications and source records attributed to Yifan Sun.

At least 181 records · Page 10Linked to original sources

arXiv2023

DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection

This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supervision. We think DETR has strong potential for CDWSOD due to an insight: the encoder and the decoder in DETR are both based on the attention mechanism and are thus capable of aggregating semantics across the entire image. The aggregation results, i.e., image-level predictions, can naturally exploit the weak supervision for domain alignment. Such motivated, we propose DETR with additional Global Aggregation (DETR-GA), a CDWSOD detector that simultaneously makes "instance-level + image-level" predictions and utilizes "strong + weak" supervisions. The key point of DETR-GA is very simple: for the encoder / decoder, we respectively add multiple class queries / a foreground query to aggregate the semantics into image-level predictions. Our query-based aggregation has two advantages. First, in the encoder, the weakly-supervised class queries are capable of roughly locating the corresponding positions and excluding the distraction from non-relevant regions. Second, through our design, the object queries and the foreground query in the decoder share consensus on the class semantics, therefore making the strong and weak supervision mutually benefit each other for domain alignment. Extensive experiments on four popular cross-domain benchmarks show that DETR-GA significantly improves CSWSOD and advances the states of the art (e.g., 29.0% --> 79.4% mAP on PASCAL VOC --> Clipart_all dataset).

cs.CV↗

arXiv2023

Reducing Discretization Error in the Frank-Wolfe Method

The Frank-Wolfe algorithm is a popular method in structurally constrained machine learning applications, due to its fast per-iteration complexity. However, one major limitation of the method is a slow rate of convergence that is difficult to accelerate due to erratic, zig-zagging step directions, even asymptotically close to the solution. We view this as an artifact of discretization; that is to say, the Frank-Wolfe \emph{flow}, which is its trajectory at asymptotically small step sizes, does not zig-zag, and reducing discretization error will go hand-in-hand in producing a more stabilized method, with better convergence properties. We propose two improvements: a multistep Frank-Wolfe method that directly applies optimized higher-order discretization schemes; and an LMO-averaging scheme with reduced discretization error, and whose local convergence rate over general convex sets accelerates from a rate of $O(1/k)$ to up to $O(1/k^{3/2})$.

math.OC↗

arXiv2023

Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis

This paper explores an expression-related self-supervised learning (SSL) method (ContraWarping) to perform expression classification in the 5th Affective Behavior Analysis in-the-wild (ABAW) competition. Affective datasets are expensive to annotate, and SSL methods could learn from large-scale unlabeled data, which is more suitable for this task. By evaluating on the Aff-Wild2 dataset, we demonstrate that ContraWarping outperforms most existing supervised methods and shows great application potential in the affective analysis area. Codes will be released on: https://github.com/youqingxiaozhua/ABAW5.

cs.CV↗

arXiv2023

Unsupervised Facial Expression Representation Learning with Contrastive Local Warping

This paper investigates unsupervised representation learning for facial expression analysis. We think Unsupervised Facial Expression Representation (UFER) deserves exploration and has the potential to address some key challenges in facial expression analysis, such as scaling, annotation bias, the discrepancy between discrete labels and continuous emotions, and model pre-training. Such motivated, we propose a UFER method with contrastive local warping (ContraWarping), which leverages the insight that the emotional expression is robust to current global transformation (affine transformation, color jitter, etc.) but can be easily changed by random local warping. Therefore, given a facial image, ContraWarping employs some global transformations and local warping to generate its positive and negative samples and sets up a novel contrastive learning framework. Our in-depth investigation shows that: 1) the positive pairs from global transformations may be exploited with general self-supervised learning (e.g., BYOL) and already bring some informative features, and 2) the negative pairs from local warping explicitly introduce expression-related variation and further bring substantial improvement. Based on ContraWarping, we demonstrate the benefit of UFER under two facial expression analysis scenarios: facial expression recognition and image retrieval. For example, directly using ContraWarping features for linear probing achieves 79.14% accuracy on RAF-DB, significantly reducing the gap towards the full-supervised counterpart (88.92% / 84.81% with/without pre-training).

cs.CV↗

arXiv2023

MMA-RNN: A Multi-level Multi-task Attention-based Recurrent Neural Network for Discrimination and Localization of Atrial Fibrillation

The automatic detection of atrial fibrillation based on electrocardiograph (ECG) signals has received wide attention both clinically and practically. It is challenging to process ECG signals with cyclical pattern, varying length and unstable quality due to noise and distortion. Besides, there has been insufficient research on separating persistent atrial fibrillation from paroxysmal atrial fibrillation, and little discussion on locating the onsets and end points of AF episodes. It is even more arduous to perform well on these two distinct but interrelated tasks, while avoiding the mistakes inherent from stage-by-stage approaches. This paper proposes the Multi-level Multi-task Attention-based Recurrent Neural Network for three-class discrimination on patients and localization of the exact timing of AF episodes. Our model captures three-level sequential features based on a hierarchical architecture utilizing Bidirectional Long and Short-Term Memory Network (Bi-LSTM) and attention layers, and accomplishes the two tasks simultaneously with a multi-head classifier. The model is designed as an end-to-end framework to enhance information interaction and reduce error accumulation. Finally, we conduct experiments on CPSC 2021 dataset and the result demonstrates the superior performance of our method, indicating the potential application of MMA-RNN to wearable mobile devices for routine AF monitoring and early diagnosis.

cs.LG↗

arXiv2023

What Do We Mean When We Talk about Trust in Social Media? A Systematic Review

Do people trust social media? If so, why, in what contexts, and how does that trust impact their lives? Researchers, companies, and journalists alike have increasingly investigated these questions, which are fundamental to understanding social media interactions and their implications for society. However, trust in social media is a complex concept, and there is conflicting evidence about the antecedents and implications of trusting social media content, users, and platforms. More problematic is that we lack basic agreement as to what trust means in the context of social media. Addressing these challenges, we conducted a systematic review to identify themes and challenges in this field. Through our analysis of 70 papers, we contribute a synthesis of how trust in social media is defined, conceptualized, and measured, a summary of trust antecedents in social media, an understanding of how trust in social media impacts behaviors and attitudes, and directions for future work.

cs.SI↗

arXiv2023

High-dimensional entanglement-enabled holography for quantum encryption

As an important imaging technique, holography has been realized with different physical dimensions of light,including polarization, wavelength, and time. Recently, quantum holography has been realized by utilizing polarization entangled state with the advantages of high robustness and enhanced spatial resolution, comparing with classical one. However, the polarization is only a two-dimensional degree of freedom, which greatly limits the capacity of quantum holography. Here, we propose a method to realize high-dimensional quantum holography by using high-dimensional orbital angular momentum (OAM) entanglement. A high capacity OAM-encoded quantum holographic system can be obtained by multiplexing a wide range of OAM-dependent holographic images. Proof-of-principle experiments with four- and six-dimensional OAM entangled states have been implemented and verify the feasibility of our idea. Our experimental results also demonstrate that the high-dimensional quantum holography shows a high robustness to classical noise. Furthermore, OAMselective holographic scheme for quantum encryption is proposed and demonstrated. Comparing with the previous schemes, the level of security of holographic imaging encryption system can be greatly improved in our high-dimensional quantum holography.

physics.optics↗

arXiv2022

Robust three-dimensional high-order solitons and breathers in driven dissipative systems: a Kerr cavity realization

We present a general approach to excite robust dissipative three-dimensional and high-order solitons and breathers in passively driven nonlinear cavities. Our findings are illustrated in the paradigmatic example provided by an optical Kerr cavity with diffraction and anomalous dispersion, with the addition of an attractive three-dimensional parabolic potential. The potential breaks the translational symmetry along all directions, and impacts the system in a qualitatively unexpected manner: three-dimensional solitons, or light-bullets, are the only existing and stable states for a given set of parameters. This property is extremely rare, if not unknown, in passive nonlinear physical systems. As a result, the excitation of the cavity with any input field leads to the deterministic formation of a target soliton or breather, with a spatiotemporal profile that unambiguously corresponds to the given cavity and pumping conditions. In addition, the tuning of the potential width along the temporal direction results in the existence of a plethora of stable asymmetric solitons. Our results may provide a solid route towards the observation of dissipative light bullets and three-dimensional breathers.

physics.optics↗

arXiv2022

Dissipative Kerr solitons, breathers and chimera states in coherently driven passive cavities with parabolic potential

We analyze the stability and dynamics of dissipative Kerr solitons in the presence of a parabolic potential. This potential stabilizes oscillatory and chaotic regimes, favoring the generation of static DKSs. Furthermore, the potential induces the emergence of new dissipative structures, such as asymmetric breathers and chimera-like states. Based on a mode decomposition of these states, we unveil the underlying modal interactions.

physics.optics↗

arXiv2022

Spatiotemporal mode decomposition of ultrashort pulses propagating in graded-index multimode fibers

We develop a spatiotemporal mode decomposition technique to study the mode power distribution of ultrashort pulses emerging from long spans of graded-index multimode fiber, for different input laser conditions. We find that beam mode power content in the dispersive pulse propagation regime can be described by the Bose-Einstein law, as a result of the process of power diffusion from linear and nonlinear mode coupling among nondegenerate mode groups. In the soliton regime, the output mode power distribution approaches the Rayleigh-Jeans law

physics.optics↗

arXiv2022

A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection

Image copy detection (ICD) aims to determine whether a query image is an edited copy of any image from a reference set. Currently, there are very limited public benchmarks for ICD, while all overlook a critical challenge in real-world applications, i.e., the distraction from hard negative queries. Specifically, some queries are not edited copies but are inherently similar to some reference images. These hard negative queries are easily false recognized as edited copies, significantly compromising the ICD accuracy. This observation motivates us to build the first ICD benchmark featuring this characteristic. Based on existing ICD datasets, this paper constructs a new dataset by additionally adding 100, 000 and 24, 252 hard negative pairs into the training and test set, respectively. Moreover, this paper further reveals a unique difficulty for solving the hard negative problem in ICD, i.e., there is a fundamental conflict between current metric learning and ICD. This conflict is: the metric learning adopts symmetric distance while the edited copy is an asymmetric (unidirectional) process, e.g., a partial crop is close to its holistic reference image and is an edited copy, while the latter cannot be the edited copy of the former (in spite the distance is equally small). This insight results in an Asymmetrical-Similarity Learning (ASL) method, which allows the similarity in two directions (the query <-> the reference image) to be different from each other. Experimental results show that ASL outperforms state-of-the-art methods by a clear margin, confirming that solving the symmetric-asymmetric conflict is critical for ICD. The NDEC dataset and code are available at https://github.com/WangWenhao0716/ASL.

cs.CV↗

arXiv2022

Biomarker-guided heterogeneity analysis of genetic regulations via multivariate sparse fusion

Heterogeneity is a hallmark of many complex diseases. There are multiple ways of defining heterogeneity, among which the heterogeneity in genetic regulations, for example GEs (gene expressions) by CNVs (copy number variations) and methylation, has been suggested but little investigated. Heterogeneity in genetic regulations can be linked with disease severity, progression, and other traits and is biologically important. However, the analysis can be very challenging with the high dimensionality of both sides of regulation as well as sparse and weak signals. In this article, we consider the scenario where subjects form unknown subgroups, and each subgroup has unique genetic regulation relationships. Further, such heterogeneity is "guided" by a known biomarker. We develop an MSF (Multivariate Sparse Fusion) approach, which innovatively applies the penalized fusion technique to simultaneously determine the number and structure of subgroups and regulation relationships within each subgroup. An effective computational algorithm is developed, and extensive simulations are conducted. The analysis of heterogeneity in the GE-CNV regulations in melanoma and GE-methylation regulations in stomach cancer using the TCGA data leads to interesting findings.

stat.ME↗

arXiv2022

Subgroup analysis for the functional linear model

Classical functional linear regression models the relationship between a scalar response and a functional covariate, where the coefficient function is assumed to be identical for all subjects. In this paper, the classical model is extended to allow heterogeneous coefficient functions across different subgroups of subjects. The greatest challenge is that the subgroup structure is usually unknown to us. To this end, we develop a penalization-based approach which innovatively applies the penalized fusion technique to simultaneously determine the number and structure of subgroups and coefficient functions within each subgroup. An effective computational algorithm is derived. We also establish the oracle properties and estimation consistency. Extensive numerical simulations demonstrate its superiority compared to several competing methods. The analysis of an air quality dataset leads to interesting findings and improved predictions.

stat.ME↗

arXiv2022

Enantioselective switch on radiations of dissipative chiral molecules

Enantiodetection is an important and challenging task across natural science. Nowadays, some chiroptical methods of enantiodetection based on decoherence-free cyclic three-level models of chiral molecules can reach the ultimate limit of the enantioselectivities in the molecular responses. They are thus more efficient than traditional chiroptical methods. However, decoherence is inevitable and can severely reduce enantioselectivities in these advanced chiroptical methods, so they only work well in the weak decoherence region. Here, we propose an enantioselective switch on the radiation of dissipative chiral molecules and develop a novel chiroptical method of enantiodetection working well in all decoherence regions. In our scheme, radiation is turned on for the selected enantiomer and simultaneously turned off for its mirror image by designing the electromagnetic fields well based on dissipative cyclic three-level models. The enantiomeric excess of a chiral mixture is determined by comparing its emissions in two cases, where the radiations of two enantiomers are turned off respectively. The corresponding enantioselectivities reach the ultimate limit in all decoherence regions, offering our scheme advantages over other chiroptical methods in enantiodetection. Our work potentially constitutes the starting point for developing more efficient chiroptical techniques for enantiodection in all decoherence regions.

quant-ph↗

arXiv2022

Semisoft Task Clustering for Multi-Task Learning

Multi-task learning (MTL) aims to improve the performance of multiple related prediction tasks by leveraging useful information from them. Due to their flexibility and ability to reduce unknown coefficients substantially, the task-clustering-based MTL approaches have attracted considerable attention. Motivated by the idea of semisoft clustering of data, we propose a semisoft task clustering approach, which can simultaneously reveal the task cluster structure for both pure and mixed tasks as well as select the relevant features. The main assumption behind our approach is that each cluster has some pure tasks, and each mixed task can be represented by a linear combination of pure tasks in different clusters. To solve the resulting non-convex constrained optimization problem, we design an efficient three-step algorithm. The experimental results based on synthetic and real-world datasets validate the effectiveness and efficiency of the proposed approach. Finally, we extend the proposed approach to a robust task clustering problem.

cs.LG↗

arXiv2022

Regression-based heterogeneity analysis to identify overlapping subgroup structure in high-dimensional data

Heterogeneity is a hallmark of complex diseases. Regression-based heterogeneity analysis, which is directly concerned with outcome-feature relationships, has led to a deeper understanding of disease biology. Such an analysis identifies the underlying subgroup structure and estimates the subgroup-specific regression coefficients. However, most of the existing regression-based heterogeneity analyses can only address disjoint subgroups; that is, each sample is assigned to only one subgroup. In reality, some samples have multiple labels, for example, many genes have several biological functions, and some cells of pure cell types transition into other types over time, which suggest that their outcome-feature relationships (regression coefficients) can be a mixture of relationships in more than one subgroups, and as a result, the disjoint subgrouping results can be unsatisfactory. To this end, we develop a novel approach to regression-based heterogeneity analysis, which takes into account possible overlaps between subgroups and high data dimensions. A subgroup membership vector is introduced for each sample, which is combined with a loss function. Considering the lack of information arising from small sample sizes, an $l_2$ norm penalty is developed for each membership vector to encourage similarity in its elements. A sparse penalization is also applied for regularized estimation and feature selection. Extensive simulations demonstrate its superiority over direct competitors. The analysis of Cancer Cell Line Encyclopedia data and lung cancer data from The Cancer Genome Atlas shows that the proposed approach can identify an overlapping subgroup structure with favorable performance in prediction and stability.

stat.ME↗

arXiv2022

Identification of cancer omics commonality and difference via community fusion

The analysis of cancer omics data is a "classic" problem, however, still remains challenging. Advancing from early studies that are mostly focused on a single type of cancer, some recent studies have analyzed data on multiple "related" cancer types/subtypes, examined their commonality and difference, and led to insightful findings. In this article, we consider the analysis of multiple omics datasets, with each dataset on one type/subtype of "related" cancers. A Community Fusion (CoFu) approach is developed, which conducts marker selection and model building using a novel penalization technique, informatively accommodates the network community structure of omics measurements, and automatically identifies the commonality and difference of cancer omics markers. Simulation demonstrates its superiority over direct competitors. The analysis of TCGA lung cancer and melanoma data leads to interesting findings

stat.ME↗

arXiv2022

Robust nonparametric integrative analysis to decipher heterogeneity and commonality across subgroups using sparse boosting

In many biomedical problems, data are often heterogeneous, with samples spanning multiple patient subgroups, where different subgroups may have different disease subtypes, stages, or other medical contexts. These subgroups may be related, but they are also expected to have differences with respect to the underlying biology. The heterogeneous data presents a precious opportunity to explore the heterogeneities and commonalities between related subgroups. Unfortunately, effective statistical analysis methods are still lacking. Recently, several novel methods based on integrative analysis have been proposed to tackle this challenging problem. Despite promising results, the existing studies are still limited by ignoring data contamination and making strict assumptions of linear effects of covariates on response. As such, we develop a robust nonparametric integrative analysis approach to identify heterogeneity and commonality, as well as select important covariates and estimate covariate effects. Possible data contamination is accommodated by adopting the Cauchy loss function, and a nonparametric model is built to accommodate nonlinear effects. The proposed approach is based on a sparse boosting technique. The advantages of the proposed approach are demonstrated in extensive simulations. The analysis of The Cancer Genome Atlas data on glioblastoma multiforme and lung adenocarcinoma shows that the proposed approach makes biologically meaningful findings with satisfactory prediction.

stat.ME↗