arXiv subjects

Qiushi Li

Publications and source records attributed to Qiushi Li.

15 recordsLinked to original sources

arXiv2026

A Zero-Shot Deep Image Prior Framework for Denoising and Deconvolution in Fluorescence Microscopy

Fluorescence microscopy images are degraded by noise and diffraction-induced blur, which compromise structural fidelity and limit quantitative analysis. Supervised deep learning methods achieve impressive restoration performance but require large-scale paired datasets that are difficult to obtain in practice. To address this issue, we propose SDIP, a zero-shot deep image prior (DIP) framework that sequentially performs denoising and deconvolution without external training data. An aSeqDIP-based module first suppresses noise while preserving fine structures through sequential autoencoding regularization. In the deconvolution stage, a wavelet-based background correction step is incorporated before the proposed RLG-DIP module performs artifact-reduced deconvolution. RLG-DIP uses the Richardson-Lucy deconvolution result as a physically consistent guidance prior, integrating the imaging model with the implicit prior of DIP to stabilize the ill-posed deconvolution process. Experiments on the BioSR dataset across multiple cellular structures demonstrate that SDIP improves both signal-to-noise ratio and resolution, achieving superior visual quality and improved quantitative performance on most evaluated structures. The proposed framework may also provide useful insights for designing physically guided DIP methods for other inverse problems.

eess.IV↗

arXiv2026

Mosaic: Cross-Modal Clustering for Efficient Video Understanding

Large vision-language models (VLMs) are enabling interactive video reasoning, giving rise to streaming long-video understanding. In this setting, frames arrive continuously, while the system preserves long-term context and generates responses under strict latency constraints. A central challenge is KVCache management: as video streams grow, KVCache expands rapidly, increasing computation and memory overhead. Existing retrieval-based approaches exploit attention sparsity and offload inactive KVCache from GPU to CPU memory, but their token-level design causes high management overhead and fragmented data movement. We present Mosaic, the first cluster-driven VLM inference system for streaming long-video understanding. Our key insight is that VLM KVCache exhibits an implicit cross-modal clustering structure: retrieved KV states form groups jointly shaped by visual coherence and semantic relevance. Based on this observation, Mosaic uses cross-modal clusters as the basic unit of KVCache organization, maintenance, and retrieval. Evaluations show that Mosaic outperforms state-of-the-art baselines, achieving up to 1.38x speedup.

cs.PF↗

arXiv2025

Computational TIRF enables optical sectioning beyond the evanescent field for widefield fluorescence microscopy

The resolving ability of widefield fluorescence microscopy is fundamentally limited by out-of-focus background owing to its low axial resolution, particularly for densely labeled biological samples. Although total internal reflection fluorescence (TIRF) microscopy provides strong near-surface sectioning, they are intrinsically restricted to shallow imaging depths. Here we present computational TIRF (cTIRF), a deep learning-based imaging modality that generates TIRF-like sectioned images directly from conventional widefield epifluorescence measurements without any optical modification. By integrating a physics-informed forward model into network training, cTIRF achieves effective background suppression and axial resolution enhancement while maintaining consistency with the measured widefield data. We demonstrate that cTIRF recovers near-surface structures with performance comparable to experimental TIRF, and further enables both single-frame and volumetric sectioned reconstruction in densely labeled samples where conventional TIRF fails. This work establishes cTIRF as a practical and deployable alternative to hardware-based optical sectioning in fluorescence microscopy, enabled by rapid adaptation to new imaging systems with minimal calibration data.

physics.optics↗

arXiv2025

Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations

With the flourishing prosperity of generative models, manipulated facial images have become increasingly accessible, raising concerns regarding privacy infringement and societal trust. In response, proactive defense strategies embed adversarial perturbations into facial images to counter deepfake manipulation. However, existing methods often face a tradeoff between imperceptibility and defense effectiveness-strong perturbations may disrupt forgeries but degrade visual fidelity. Recent studies have attempted to address this issue by introducing additional visual loss constraints, yet often overlook the underlying gradient conflicts among losses, ultimately weakening defense performance. To bridge the gap, we propose a gradient-projection-based adversarial proactive defense (GRASP) method that effectively counters facial deepfakes while minimizing perceptual degradation. GRASP is the first approach to successfully integrate both structural similarity loss and low-frequency loss to enhance perturbation imperceptibility. By analyzing gradient conflicts between defense effectiveness loss and visual quality losses, GRASP pioneers the design of the gradient-projection mechanism to mitigate these conflicts, enabling balanced optimization that preserves image fidelity without sacrificing defensive performance. Extensive experiments validate the efficacy of GRASP, achieving a PSNR exceeding 40 dB, SSIM of 0.99, and a 100% defense success rate against facial attribute manipulations, significantly outperforming existing approaches in visual quality.

cs.CR↗

arXiv2025

What Makes Code Generation Ethically Sourced?

Several code generation models have been proposed to help reduce time and effort in solving software-related tasks. To ensure responsible AI, there are growing interests over various ethical issues (e.g., unclear licensing, privacy, fairness, and environment impact). These studies have the overarching goal of ensuring ethically sourced generation, which has gained growing attentions in speech synthesis and image generation. In this paper, we introduce the novel notion of Ethically Sourced Code Generation (ES-CodeGen) to refer to managing all processes involved in code generation model development from data collection to post-deployment via ethical and sustainable practices. To build a taxonomy of ES-CodeGen, we perform a two-phase literature review where we read 803 papers across various domains and specific to AI-based code generation. We identified 71 relevant papers with 10 initial dimensions of ES-CodeGen. To refine our dimensions and gain insights on consequences of ES-CodeGen, we surveyed 32 practitioners, which include six developers who submitted GitHub issues to opt-out from the Stack dataset (these impacted users have real-world experience of ethically sourcing issues in code generation models). The results lead to 11 dimensions of ES-CodeGen with a new dimension on code quality as practitioners have noted its importance. We also identified consequences, artifacts, and stages relevant to ES-CodeGen. Our post-survey reflection showed that most practitioners tend to ignore social-related dimensions despite their importance. Most practitioners either agreed or strongly agreed that our survey help improve their understanding of ES-CodeGen. Our study calls for attentions of various ethical issues towards ES-CodeGen.

cs.SE↗

arXiv2025

CSVAR: Enhancing Visual Privacy in Federated Learning via Adaptive Shuffling Against Overfitting

Although federated learning preserves training data within local privacy domains, the aggregated model parameters may still reveal private characteristics. This vulnerability stems from clients' limited training data, which predisposes models to overfitting. Such overfitting enables models to memorize distinctive patterns from training samples, thereby amplifying the success probability of privacy attacks like membership inference. To enhance visual privacy protection in FL, we present CSVAR(Channel-Wise Spatial Image Shuffling with Variance-Guided Adaptive Region Partitioning), a novel image shuffling framework to generate obfuscated images for secure data transmission and each training epoch, addressing both overfitting-induced privacy leaks and raw image transmission risks. CSVAR adopts region-variance as the metric to measure visual privacy sensitivity across image regions. Guided by this, CSVAR adaptively partitions each region into multiple blocks, applying fine-grained partitioning to privacy-sensitive regions with high region-variances for enhancing visual privacy protection and coarse-grained partitioning to privacy-insensitive regions for balancing model utility. In each region, CSVAR then shuffles between blocks in both the spatial domains and chromatic channels to hide visual spatial features and disrupt color distribution. Experimental evaluations conducted on diverse real-world datasets demonstrate that CSVAR is capable of generating visually obfuscated images that exhibit high perceptual ambiguity to human eyes, simultaneously mitigating the effectiveness of adversarial data reconstruction attacks and achieving a good trade-off between visual privacy protection and model utility.

cs.CR↗

arXiv2025

Guiding ChatGPT to Fix Web UI Tests via Explanation-Consistency Checking

The rapid evolution of Web UI incurs time and effort in UI test maintenance. Prior techniques in Web UI test repair focus on locating the target elements on the new Webpage that match the old ones so that the corresponding broken statements can be repaired. These techniques usually rely on prioritizing certain attributes (e.g., XPath) during matching where the similarity of certain attributes is ranked before other attributes, indicating that there may be bias towards certain attributes during matching. To mitigate the bias, we present the first study that investigates the feasibility of using prior Web UI repair techniques for initial matching and then using ChatGPT to perform subsequent matching. Our key insight is that given a list of elements matched by prior techniques, ChatGPT can leverage language understanding to perform subsequent matching and use its code generation model for fixing the broken statements. To mitigate hallucination in ChatGPT, we design an explanation validator that checks if the provided explanation for the matching results is consistent, and provides hints to ChatGPT via a self-correction prompt to further improve its results. Our evaluation on a widely used dataset shows that the ChatGPT-enhanced techniques improve the effectiveness of existing Web test repair techniques. Our study also shares several important insights in improving future Web UI test repair techniques.

cs.SE↗

arXiv2024

Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection

Previous studies in deepfake detection have shown promising results when testing face forgeries from the same dataset as the training. However, the problem remains challenging when one tries to generalize the detector to forgeries from unseen datasets and created by unseen methods. In this work, we present a novel general deepfake detection method, called \textbf{C}urricular \textbf{D}ynamic \textbf{F}orgery \textbf{A}ugmentation (CDFA), which jointly trains a deepfake detector with a forgery augmentation policy network. Unlike the previous works, we propose to progressively apply forgery augmentations following a monotonic curriculum during the training. We further propose a dynamic forgery searching strategy to select one suitable forgery augmentation operation for each image varying between training stages, producing a forgery augmentation policy optimized for better generalization. In addition, we propose a novel forgery augmentation named self-shifted blending image to simply imitate the temporal inconsistency of deepfake generation. Comprehensive experiments show that CDFA can significantly improve both cross-datasets and cross-manipulations performances of various naive deepfake detectors in a plug-and-play way, and make them attain superior performances over the existing methods in several benchmark datasets.

cs.CV↗

arXiv2024

You Can Use But Cannot Recognize: Preserving Visual Privacy in Deep Neural Networks

Image data have been extensively used in Deep Neural Network (DNN) tasks in various scenarios, e.g., autonomous driving and medical image analysis, which incurs significant privacy concerns. Existing privacy protection techniques are unable to efficiently protect such data. For example, Differential Privacy (DP) that is an emerging technique protects data with strong privacy guarantee cannot effectively protect visual features of exposed image dataset. In this paper, we propose a novel privacy-preserving framework VisualMixer that protects the training data of visual DNN tasks by pixel shuffling, while not injecting any noises. VisualMixer utilizes a new privacy metric called Visual Feature Entropy (VFE) to effectively quantify the visual features of an image from both biological and machine vision aspects. In VisualMixer, we devise a task-agnostic image obfuscation method to protect the visual privacy of data for DNN training and inference. For each image, it determines regions for pixel shuffling in the image and the sizes of these regions according to the desired VFE. It shuffles pixels both in the spatial domain and in the chromatic channel space in the regions without injecting noises so that it can prevent visual features from being discerned and recognized, while incurring negligible accuracy loss. Extensive experiments on real-world datasets demonstrate that VisualMixer can effectively preserve the visual privacy with negligible accuracy loss, i.e., at average 2.35 percentage points of model accuracy loss, and almost no performance degradation on model training.

cs.CR↗

arXiv2022

Efficient implementation of portfolio strategies involving cryptocurrencies and VIX INDEX and Gold

This research mainly explores the characteristics of different strategies and whether VIX INDEX positively influences the investment portfolio in any period. Our portfolio has six significant cryptocurrencies, VIX INDEX and gold. We perform parameter estimation on all raw data and bring the two types into different investment strategies, complete them effectively according to other characteristics, and compare the results. At the same time, we make two different portfolios, one contains VIX INDEX, and one does not have VIX INDEX. We use different portfolios in different portfolio strategies and find that VIX INDEX can positively impact the investment portfolio of cryptocurrencies, no matter in the standard market or the downward market. The research shows that gold has the same attributes as VIX INDEX and should have a specific positive effect, but no comparative experiment has been done.

q-fin.PM↗

arXiv2022

STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition

Recent studies shows that the majority of existing deep steganalysis models have a large amount of redundancy, which leads to a huge waste of storage and computing resources. The existing model compression method cannot flexibly compress the convolutional layer in residual shortcut block so that a satisfactory shrinking rate cannot be obtained. In this paper, we propose STD-NET, an unsupervised deep-learning architecture search approach via hierarchical tensor decomposition for image steganalysis. Our proposed strategy will not be restricted by various residual connections, since this strategy does not change the number of input and output channels of the convolution block. We propose a normalized distortion threshold to evaluate the sensitivity of each involved convolutional layer of the base model to guide STD-NET to compress target network in an efficient and unsupervised approach, and obtain two network structures of different shapes with low computation cost and similar performance compared with the original one. Extensive experiments have confirmed that, on one hand, our model can achieve comparable or even better detection performance in various steganalytic scenarios due to the great adaptivity of the obtained network architecture. On the other hand, the experimental results also demonstrate that our proposed strategy is more efficient and can remove more redundancy compared with previous steganalytic network compression methods.

cs.CV↗

arXiv2021

Transfer Learning in High-dimensional Semi-parametric Graphical Models with Application to Brain Connectivity Analysis

Transfer learning has drawn growing attention with the target of improving statistical efficiency of one study (dataset) by digging information from similar and related auxiliary studies (datasets). In the article, we consider transfer learning problem in estimating undirected semi-parametric graphical model. We propose an algorithm called Trans-Copula-CLIME for estimating undirected graphical model while digging information from similar auxiliary studies, characterizing the similarity between the target graph and each auxiliary graph by the sparsity of a divergence matrix. The proposed method relaxes the restrictive assumption that data follows a Gaussian distribution, which deviates from reality for the fMRI dataset related to Attention Deficit Hyperactivity Disorder (ADHD) considered here. Nonparametric rank-based correlation coefficient estimators are utilized in the Trans-Copula-CLIME procedure to achieve robustness against normality. We establish the convergence rate of the Trans-Copula-CLIME estimator under some mild conditions, which demonstrates that when the similarity between the auxiliary studies and the target study is sufficiently high and the number of informative auxiliary samples is sufficiently large, then the Trans-Copula-CLIME estimator shows great advantage over the existing non-transfer-learning ones. Simulation studies also show that Trans-Copula-CLIME estimator has better performance especially when data are not from Gaussian distribution. At last, the proposed method is applied to infer functional brain connectivity pattern for ADHD patients in the target Beijing site by leveraging the fMRI datasets from New York site.

stat.ME↗

arXiv2020

CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images

Over the past few years, detection performance improvements of deep-learning based steganalyzers have been usually achieved through structure expansion. However, excessive expanded structure results in huge computational cost, storage overheads, and consequently difficulty in training and deployment. In this paper we propose CALPA-NET, a ChAnneL-Pruning-Assisted deep residual network architecture search approach to shrink the network structure of existing vast, over-parameterized deep-learning based steganalyzers. We observe that the broad inverted-pyramid structure of existing deep-learning based steganalyzers might contradict the well-established model diversity oriented philosophy, and therefore is not suitable for steganalysis. Then a hybrid criterion combined with two network pruning schemes is introduced to adaptively shrink every involved convolutional layer in a data-driven manner. The resulting network architecture presents a slender bottleneck-like structure. We have conducted extensive experiments on BOSSBase+BOWS2 dataset, more diverse ALASKA dataset and even a large-scale subset extracted from ImageNet CLS-LOC dataset. The experimental results show that the model structure generated by our proposed CALPA-NET can achieve comparative performance with less than two percent of parameters and about one third FLOPs compared to the original steganalytic model. The new model possesses even better adaptivity, transferability, and scalability.

cs.MM↗

arXiv2015

Examples of Complete Solvability of 2D Classical Superintegrable Systems

Classical (maximal) superintegrable systems in $n$ dimensions are Hamiltonian systems with $2n-1$ independent constants of the motion, globally defined, the maximum number possible. They are very special because they can be solved algebraically. In this paper we show explicitly, mostly through examples of 2nd order superintegrable systems in 2 dimensions, how the trajectories can be determined in detail using rather elementary algebraic, geometric and analytic methods applied to the closed quadratic algebra of symmetries of the system. We treat a family of 2nd order degenerate systems: oscillator analogies on Darboux, nonzero constant curvature, and flat spaces, related to one another via contractions, and obeying Kepler's laws. Then we treat two 2nd order nondegenerate systems, an analogy of a caged Coulomb problem on the 2-sphere and its contraction to a Euclidean space caged Coulomb problem. In all cases the symmetry algebra structure provides detailed information about the trajectories. An interesting example is the occurrence of ''metronome orbits'', trajectories confined to an arc rather than a loop, which are indicated clearly from the structure equations but might be overlooked using more traditional methods. We also treat the Post-Winternitz system, an example of a classical 4th order superintegrable system that cannot be solved using separation of variables. Finally we treat a superintegrable system, related to the addition theorem for elliptic functions, whose constants of the motion are only rational in the momenta, a system of special interest because its constants of the motion generate a closed polynomial algebra. This paper contains many new results but we have tried to present most of the materials in a fashion that is easily accessible to nonexperts, in order to provide entrée to superintegrablity theory.

math-ph↗

arXiv2015

Wilson polynomials/functions and intertwining operators for the generic quantum superintegrable system on the 2-sphere

It has been known since 2007 that the Wilson and Racah polynomials can be characterized as basis functions for irreducible representations of the quadratic symmetry algebra of the quantum superintegrable system on the 2-sphere, $HΨ=EΨ$, with generic 3-parameter potential. Clearly, the polynomials are expansion coefficients for one eigenbasis of a symmetry operator $L_1$ of $H$ in terms of an eigenbasis of another symmetry operator $L_2$, but the exact relationship appears not to have been made explicit. We work out the details of the expansion to show, explicitly, how the polynomials arise and how the principal properties of these functions: the measure, 3-term recurrence relation, 2nd order difference equation, duality of these relations, permutation symmetry, intertwining operators and an alternate derivation of Wilson functions -- follow from the symmetry of this quantum system. There is active interest in the relation between multivariable Wilson polynomials and the quantum superintegrable system on the $n$-sphere with generic potential, and these results should aid in the generalization. Contracting function space realizations of irreducible representations of this quadratic algebra to the other superintegrable systems one can obtain the full Askey scheme of orthogonal hypergeometric polynomials. All of these contractions of superintegrable systems with potential are uniquely induced by Wigner Lie algebra contractions of $so(3, C )$ and $e(2, C)$. All of the polynomials produced are interpretable as quantum expansion coefficients. It is important to extend this process to higher dimensions.

math-ph↗