arXiv subjects

Tao Yan

Publications and source records attributed to Tao Yan.

At least 19 recordsLinked to original sources

arXiv2026

Glass Surface Detection Grounded in 3D Visual Geometry

Glass surface detection (GSD) is critical for scene understanding and reconstruction, and yet remains challenging due to the transparency and reflectivity of glass surfaces. Existing GSD methods typically rely on 2D appearance cues, which may fail in geometrically ambiguous scenes. In this paper, we propose a paradigm shift: grounding GSD in 3D visual geometry to explicitly model the physical existence of glass surfaces. Our method first distills rich 3D priors from the visual geometry grounded transformer (VGGT) and generates glass-aware 3D representations. It then exploits multi-tasking learning with a novel glass detection head, consisting of two core modules: a Frequency Self-Attention Module (FSAM) that identifies glass-specific spectral features for glass surface localization, and a Geometry Grounding Block (GeGB) that selectively grounds 2D features in 3D geometry for glass surface segmentation. Extensive experiments demonstrate that our method achieves state-of-the-art performance across seven standard GSD benchmarks, generalizes well to video/multi-modal data, and substantially improves reconstruction in glass scenes. Code is available in https://github.com/YT3DVision/VGGT_GLASS.

cs.CV↗

arXiv2026

FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection

Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex background interference. To address these issues, this paper proposes FSDETR, a frequency-spatial feature enhancement framework built upon the RT-DETR baseline. By establishing a collaborative modeling mechanism, the method effectively leverages complementary structural information. Specifically, a Spatial Hierarchical Attention Block (SHAB) captures both local details and global dependencies to strengthen semantic representation. Furthermore, to mitigate occlusion in dense scenes, the Deformable Attention-based Intra-scale Feature Interaction (DA-AIFI) focuses on informative regions via dynamic sampling. Finally, the Frequency-Spatial Feature Pyramid Network (FSFPN) integrates frequency filtering with spatial edge extraction via the Cross-domain Frequency-Spatial Block (CFSB) to preserve fine-grained details. Experimental results show that with only 14.7M parameters, FSDETR achieves 13.9% APS on VisDrone 2019 and 48.95% AP50 tiny on TinyPerson, showing strong performance on small-object benchmarks. The code and models are available at https://github.com/YT3DVision/FSDETR.

cs.CV↗

arXiv2026

SEP-YOLO: Fourier-Domain Feature Representation for Transparent Object Instance Segmentation

Transparent object instance segmentation presents significant challenges in computer vision, due to the inherent properties of transparent objects, including boundary blur, low contrast, and high dependence on background context. Existing methods often fail as they depend on strong appearance cues and clear boundaries. To address these limitations, we propose SEP-YOLO, a novel framework that integrates a dual-domain collaborative mechanism for transparent object instance segmentation. Our method incorporates a Frequency Domain Detail Enhancement Module, which separates and enhances weak highfrequency boundary components via learnable complex weights. We further design a multi-scale spatial refinement stream, which consists of a Content-Aware Alignment Neck and a Multi-scale Gated Refinement Block, to ensure precise feature alignment and boundary localization in deep semantic features. We also provide high-quality instance-level annotations for the Trans10K dataset, filling the critical data gap in transparent object instance segmentation. Extensive experiments on the Trans10K and GVD datasets show that SEP-YOLO achieves state-of-the-art (SOTA) performance.

cs.CV↗

arXiv2026

MVGD-Net: A Novel Motion-aware Video Glass Surface Detection Method

Glass surface ubiquitous in both daily life and professional environments presents a potential threat to vision-based systems, such as robot and drone navigation. To solve this challenge, most recent studies have shown significant interest in Video Glass Surface Detection (VGSD). We observe that objects in the reflection (or transmission) layer appear farther from the glass surfaces. Consequently, in video motion scenarios, the notable reflected (or transmitted) objects on the glass surface move slower than objects in non-glass regions within the same spatial plane, and this motion inconsistency can effectively reveal the presence of glass surfaces. Based on this observation, we propose a novel network, named MVGD-Net, for detecting glass surfaces in videos by leveraging motion inconsistency cues. Our MVGD-Net features three novel modules: the Cross-scale Multimodal Fusion Module (CMFM) that integrates extracted spatial features and estimated optical flow maps, the History Guided Attention Module (HGAM) and Temporal Cross Attention Module (TCAM), both of which further enhances temporal features. A Temporal-Spatial Decoder (TSD) is also introduced to fuse the spatial and temporal features for generating the glass region mask. Furthermore, for learning our network, we also propose a large-scale dataset, which comprises 312 diverse glass scenarios with a total of 19,268 frames. Extensive experiments demonstrate that our MVGD-Net outperforms relevant state-of-the-art methods.

cs.CV↗

arXiv2025

A Lightweight Multi-Scale Attention Framework for Real-Time Spinal Endoscopic Instance Segmentation

Real-time instance segmentation for spinal endoscopy is important for identifying and protecting critical anatomy during surgery, but it is difficult because of the narrow field of view, specular highlights, smoke/bleeding, unclear boundaries, and large scale changes. Deployment is also constrained by limited surgical hardware, so the model must balance accuracy and speed and remain stable under small-batch (even batch-1) training. We propose LMSF-A, a lightweight multi-scale attention framework co-designed across backbone, neck, and head. The backbone uses a C2f-Pro module that combines RepViT-style re-parameterized convolution (RVB) with efficient multi-scale attention (EMA), enabling multi-branch training while collapsing into a single fast path for inference. The neck improves cross-scale consistency and boundary detail using Scale-Sequence Feature Fusion (SSFF) and Triple Feature Encoding (TFE), which strengthens high-resolution features. The head adopts a Lightweight Multi-task Shared Head (LMSH) with shared convolutions and GroupNorm to reduce parameters and support batch-1 stability. We also release the clinically reviewed PELD dataset (61 patients, 610 images) with instance masks for adipose tissue, bone, ligamentum flavum, and nerve. Experiments show that LMSF-A is highly competitive (or even better than) in all evaluation metrics and much lighter than most instance segmentation methods requiring only 1.8M parameters and 8.8 GFLOPs, and it generalizes well to a public teeth benchmark. Code and dataset: https://github.com/hhwmortal/PELD-Instance-segmentation.

cs.CV↗

arXiv2025

Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery

Glass surfaces are ubiquitous in daily life, typically appearing colorless, transparent, and lacking distinctive features. These characteristics make glass surface detection a challenging computer vision task. Existing glass surface detection methods always rely on boundary cues (\textit{e.g.}, window and door frames) or reflection cues to locate glass surfaces, but they fail to fully exploit the intrinsic properties of the glass itself for accurate localization. We observed that in most real-world scenes, the illumination intensity in front of the glass surface differs from that behind it, which results in variations in the reflections visible on the glass surface. Specifically, when standing on the brighter side of the glass and applying a flash towards the darker side, existing reflections on the glass surface tend to disappear. Conversely, while standing on the darker side and applying a flash towards the brighter side, distinct reflections will appear on the glass surface. Based on this phenomenon, we propose \textit{NFGlassNet}, a novel method for glass surface detection that leverages the reflection dynamics present in flash/no-flash imagery. Specifically, we propose a Reflection Contrast Mining Module (RCMM) for extracting reflections, and a Reflection Guided Attention Module (RGAM) for fusing features from reflection and glass surface for accurate glass surface detection. For learning our network, we also construct a dataset consisting of $\sim$3.3$K$ no-flash and flash image pairs captured from various scenes with corresponding ground truth annotations. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. Our code, model, and dataset will be available upon acceptance of the manuscript.

cs.CV↗

arXiv2025

Control Analysis and Design for Autonomous Vehicles Subject to Imperfect AI-Based Perception

Safety is a critical concern in autonomous vehicle (AV) systems, especially when AI-based sensing and perception modules are involved. However, due to the black box nature of AI algorithms, it makes closed-loop analysis and synthesis particularly challenging, for example, establishing closed-loop stability and ensuring performance, while they are fundamental to AV safety. To approach this difficulty, this paper aims to develop new modeling, analysis, and synthesis tools for AI-based AVs. Inspired by recent developments in perception error models (PEMs), the focus is shifted from directly modeling AI-based perception processes to characterizing the perception errors they produce. Two key classes of AI-induced perception errors are considered: misdetection and measurement noise. These error patterns are modeled using continuous-time Markov chains and Wiener processes, respectively. By means of that, a PEM-augmented driving model is proposed, with which we are able to establish the closed-loop stability for a class of AI-driven AV systems via stochastic calculus. Furthermore, a performance-guaranteed output feedback control synthesis method is presented, which ensures both stability and satisfactory performance. The method is formulated as a convex optimization problem, allowing for efficient numerical solutions. The results are then applied to an adaptive cruise control (ACC) scenario, demonstrating their effectiveness and robustness despite the corrupted and misleading perception.

eess.SY↗

arXiv2025

Approaches to Analysis and Design of AI-Based Autonomous Vehicles

Artificial intelligence (AI) models are becoming key components in an autonomous vehicle (AV), especially in handling complicated perception tasks. However, closing the loop through AI-based feedback may pose significant risks on reliability of autonomous driving due to very limited understanding about the mechanism of AI-driven perception processes. To overcome it, this paper aims to develop tools for modeling, analysis, and synthesis for a class of AI-based AV; in particular, their closed-loop properties, e.g., stability, robustness, and performance, are rigorously studied in the statistical sense. First, we provide a novel modeling means for the AI-driven perception processes by looking at their error characteristics. Specifically, three fundamental AI-induced perception uncertainties are recognized and modeled by Markov chains, Gaussian processes, and bounded disturbances, respectively. By means of that, the closed-loop stochastic stability (SS) is established in the sense of mean square, and then, an SS control synthesis method is presented within the framework of linear matrix inequalities (LMIs). Besides the SS properties, the robustness and performance of AI-based AVs are discussed in terms of a stochastic guaranteed cost, and criteria are given to test the robustness level of an AV when in the presence of AI-induced uncertainties. Furthermore, the stochastic optimal guaranteed cost control is investigated, and an efficient design procedure is developed innovatively based on LMI techniques and convex optimization. Finally, to illustrate the effectiveness, the developed results are applied to an example of car following control, along with extensive simulation.

eess.SY↗

arXiv2025

Reprojection-Guided 3D Gaussian Splatting Diffusion for Weakly Supervised Single-Image Normal Estimation

We propose CLONE, a Continuous Latent Optimization framework for Normal Estimation via 3D Gaussian splatting. The core idea is to construct an image-geometry-image consistency strategy that unifies explicit geometric representation with differentiable rendering, thereby enabling weakly supervised learning without normal ground truth. Specifically, CLONE comprises four components. First, by introducing a differentiable light interaction model with a learnable modulation kernel, we perform a unified reparameterization of the 3DGS parameter space. Second, the conditional single-step deterministic refinement network integrates denoising architectures with differentiable reprojection constraints to refine the initial normals, thereby adaptively recovering the high-frequency details erased by the inherently smooth Gaussian primitives. Third, the cross-domain gating fusion mechanism adaptively combines the two complementary normal estimates, reconciling the geometrically consistent yet over-smooth 3DGS estimate with the detailed yet potentially geometry-inconsistent refinement. Finally, all components are jointly optimized under a unified photometric reprojection objective with geometric consistency regularizations in a fully differentiable pathway, achieving an end-to-end optimization closed loop without relying on external normal labels.

cs.CV↗

arXiv2025

Ranked Set Sampling-Based Multilayer Perceptron: Improving Generalization via Variance-Based Bounds

Multilayer perceptron (MLP), one of the most fundamental neural networks, is extensively utilized for classification and regression tasks. In this paper, we establish a new generalization error bound, which reveals how the variance of empirical loss influences the generalization ability of the learning model. Inspired by this learning bound, we advocate to reduce the variance of empirical loss to enhance the ability of MLP. As is well-known, bagging is a popular ensemble method to realize variance reduction. However, bagging produces the base training data sets by the Simple Random Sampling (SRS) method, which exhibits a high degree of randomness. To handle this issue, we introduce an ordered structure in the training data set by Rank Set Sampling (RSS) to further reduce the variance of loss and develop a RSS-MLP method. Theoretical results show that the variance of empirical exponential loss and the logistic loss estimated by RSS are smaller than those estimated by SRS, respectively. To validate the performance of RSS-MLP, we conduct comparison experiments on twelve benchmark data sets in terms of the two convex loss functions under two fusion methods. Extensive experimental results and analysis illustrate the effectiveness and rationality of the propose method.

cs.LG↗

arXiv2025

Tracing Cross-chain Transactions between EVM-based Blockchains: An Analysis of Ethereum-Polygon Bridges

Ethereum's scalability has been a major concern due to its limited transaction throughput and high fees. To address these limitations, Polygon has emerged as a sidechain solution that facilitates asset transfers between Ethereum and Polygon, thereby improving scalability and reducing costs. However, current cross-chain transactions, particularly those between Ethereum and Polygon, lack transparency and traceability. This paper proposes a method to track cross-chain transactions across EVM-compatible blockchains. It leverages the unique feature that user addresses are consistent across EVM-compatible blockchains. We develop a matching heuristic algorithm that links transactions between the source and target chains by combining transaction time, value, and token identification. Applying our methodology to over 2 million cross-chain transactions (August 2020-August 2023) between Ethereum and Polygon, we achieve matching rates of up to 99.65% for deposits and 92.78% for withdrawals, across different asset types including Ether, ERC-20 tokens, and NFTs. In addition, we provide a comprehensive analysis of various properties and characteristics of cross-chain transactions. Our methodology and findings contribute to a better understanding of cross-chain transaction dynamics and bridge performance, with implications for improving bridge efficiency and security in cross-chain operations.

cs.DC↗

arXiv2025

Topological exciton bands and many-body exciton phases in transition metal dichalcogenide trilayer heterostructures

Twisted multilayer transition metal dichalcogenides (TMDs) are a promising platform for realizing topological exciton phases. Here we propose that twisted TMD heterotrilayers WX$_2$/MX$_2$/WX$_2$ with layer symmetry represents a realistic system for realizing topological exciton bands and interesting many-body excitonic phases, simply by tuning the twist angle. These symmetric heterotrilayers form a type-II band alignment, where the electrons are confined in the middle layer and holes are distributed among the outer two layers, for the lowest energy excitons. The outer two layers are then rotated at different centers by opposite angles, forming a helical structure. Interlayer excitons with opposite dipoles are hybridized by the coupling between outer two layers, resulting in topological moir\'e exciton bands. Furthermore, by constructing a three-orbital tight-binding model, we map the many-body phase diagram of interacting dipolar and quadrupolar excitons at different twist angles and exciton densities and reveal the existence of sublattice-dependent staggered superfluid and Mott insulator phases. The recent experimental observation of quadrupolar excitons in symmetric heterotrilayers brings the intriguing phases predicted in this study within immediate experimental reach.

cond-mat.mes-hall↗

arXiv2025

Network Analysis of Uniswap: Centralization and Fragility in the Decentralized Exchange Market

The Uniswap is a Decentralized Exchange (DEX) protocol that facilitates automatic token exchange without the need for traditional order books. Every pair of tokens forms a liquidity pool on Uniswap, and each token can be paired with any other token to create liquidity pools. This characteristic motivates us to employ a complex network approach to analyze the features of the Uniswap market. This research presents a comprehensive analysis of the Uniswap network using complex network methods. The network on October 31, 2023, is built to observe its recent features, showcasing both scale-free and core-periphery properties. By employing node and edge-betweenness metrics, we detect the most important tokens and liquidity pools. Additionally, we construct daily networks spanning from the beginning of Uniswap V2 on May 5, 2020, until October 31, 2023, and our findings demonstrate that the network becomes increasingly fragile over time. Furthermore, we conduct a robustness analysis by simulating the deletion of nodes to estimate the impact of some extreme events such as the Terra collapse. The results indicate that the Uniswap network exhibits robustness, yet it is notably fragile when deleting tokens with high betweenness centrality. This finding highlights that, despite being a decentralized exchange, Uniswap exhibits significant centralization tendencies in terms of token network connectivity and the distribution of TVL across nodes (tokens) and edges (liquidity pools).

cs.CE↗

arXiv2024

Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble

As real-world knowledge is constantly evolving, ensuring the timeliness and accuracy of a model's knowledge is crucial. This has made knowledge editing in large language models increasingly important. However, existing knowledge editing methods face several challenges, including parameter localization coupling, imprecise localization, and a lack of dynamic interaction across layers. In this paper, we propose a novel knowledge editing method called Knowledge Neuronal Ensemble (KNE). A knowledge neuronal ensemble represents a group of neurons encoding specific knowledge, thus mitigating the issue of frequent parameter modification caused by coupling in parameter localization. The KNE method enhances the precision and accuracy of parameter localization by computing gradient attribution scores for each parameter at each layer. During the editing process, only the gradients and losses associated with the knowledge neuronal ensemble are computed, with error backpropagation performed accordingly, ensuring dynamic interaction and collaborative updates among parameters. Experimental results on three widely used knowledge editing datasets show that the KNE method significantly improves the accuracy of knowledge editing and achieves, or even exceeds, the performance of the best baseline methods in portability and locality metrics.

cs.CL↗

arXiv2024

k-HyperEdge Medoids for Clustering Ensemble

Clustering ensemble has been a popular research topic in data science due to its ability to improve the robustness of the single clustering method. Many clustering ensemble methods have been proposed, most of which can be categorized into clustering-view and sample-view methods. The clustering-view method is generally efficient, but it could be affected by the unreliability that existed in base clustering results. The sample-view method shows good performance, while the construction of the pairwise sample relation is time-consuming. In this paper, the clustering ensemble is formulated as a k-HyperEdge Medoids discovery problem and a clustering ensemble method based on k-HyperEdge Medoids that considers the characteristics of the above two types of clustering ensemble methods is proposed. In the method, a set of hyperedges is selected from the clustering view efficiently, then the hyperedges are diffused and adjusted from the sample view guided by a hyperedge loss function to construct an effective k-HyperEdge Medoid set. The loss function is mainly reduced by assigning samples to the hyperedge with the highest degree of belonging. Theoretical analyses show that the solution can approximate the optimal, the assignment method can gradually reduce the loss function, and the estimation of the belonging degree is statistically reasonable. Experiments on artificial data show the working mechanism of the proposed method. The convergence of the method is verified by experimental analysis of twenty data sets. The effectiveness and efficiency of the proposed method are also verified on these data, with nine representative clustering ensemble algorithms as reference.

cs.LG↗

arXiv2024

An Improved Algorithm to Identify More Arbitrage Opportunities on Decentralized Exchanges

In decentralized exchanges (DEXs), the arbitrage paths exist abundantly in the form of both arbitrage loops (e.g. the arbitrage path starts from token A and back to token A again in the end, A, B,..., A) and non-loops (e.g. the arbitrage path starts from token A and stops at a different token N, A, B,..., N). The Moore-Bellman-Ford algorithm, often coupled with the ``walk to the root" technique, is commonly employed for detecting arbitrage loops in the token graph of decentralized exchanges (DEXs) such as Uniswap. However, a limitation of this algorithm is its ability to recognize only a limited number of arbitrage loops in each run. Additionally, it cannot specify the starting token of the detected arbitrage loops, further constraining its effectiveness in certain scenarios. Another limitation of this algorithm is its incapacity to detect non-loop arbitrage paths between any specified pairs of tokens. In this paper, we develop a new method to solve these problems by combining the line graph and a modified Moore-Bellman-Ford algorithm (MMBF). This method can help to find more arbitrage loops by detecting at least one arbitrage loop starting from any specified tokens in the DEXs and can detect the non-loop arbitrage paths between any pair of tokens. Then, we applied our algorithm to Uniswap V2 and found more arbitrage loops and non-loops indeed compared with applying the Moore-Bellman-Ford (MBF) combined algorithm. The found arbitrage profit by our method in some arbitrage paths can be even as high as one million dollars, far larger than that found by the MBF combined algorithm. Finally, we statistically compare the distribution of arbitrage path lengths and the arbitrage profit detected by both our method and the MBF combined algorithm, and depict how potential arbitrage opportunities change with time by our method.

q-fin.CP↗

arXiv2024

Profit Maximization In Arbitrage Loops

Cyclic arbitrage chances exist abundantly among decentralized exchanges (DEXs), like Uniswap V2. For an arbitrage cycle (loop), researchers or practitioners usually choose a specific token, such as Ether as input, and optimize their input amount to get the net maximal amount of the specific token as arbitrage profit. By considering the tokens' prices from CEXs in this paper, the new arbitrage profit, called monetized arbitrage profit, will be quantified as the product of the net number of a specific token we got from the arbitrage loop and its corresponding price in CEXs. Based on this concept, we put forward three different strategies to maximize the monetized arbitrage profit for each arbitrage loop. The first strategy is called the MaxPrice strategy. Under this strategy, arbitrageurs start arbitrage only from the token with the highest CEX price. The second strategy is called the MaxMax strategy. Under this strategy, we calculate the monetized arbitrage profit for each token as input in turn in the arbitrage loop. Then, we pick up the most maximal monetized arbitrage profit among them as the monetized arbitrage profit of the MaxMax strategy. The third one is called the Convex Optimization strategy. By mapping the MaxMax strategy to a convex optimization problem, we proved that the Convex Optimization strategy could get more profit in theory than the MaxMax strategy, which is proved again in a given example. We also proved that if no arbitrage profit exists according to the MaxMax strategy, then the Convex Optimization strategy can not detect any arbitrage profit, either. However, the empirical data analysis denotes that the profitability of the Convex Optimization strategy is almost equal to that of the MaxMax strategy, and the MaxPrice strategy is not reliable in getting the maximal monetized arbitrage profit compared to the MaxMax strategy.

q-fin.CP↗

arXiv2024

MDeRainNet: An Efficient Macro-pixel Image Rain Removal Network

Since rainy weather always degrades image quality and poses significant challenges to most computer vision-based intelligent systems, image de-raining has been a hot research topic. Fortunately, in a rainy light field (LF) image, background obscured by rain streaks in one sub-view may be visible in the other sub-views, and implicit depth information and recorded 4D structural information may benefit rain streak detection and removal. However, existing LF image rain removal methods either do not fully exploit the global correlations of 4D LF data or only utilize partial sub-views, resulting in sub-optimal rain removal performance and no-equally good quality for all de-rained sub-views. In this paper, we propose an efficient network, called MDeRainNet, for rain streak removal from LF images. The proposed network adopts a multi-scale encoder-decoder architecture, which directly works on Macro-pixel images (MPIs) to improve the rain removal performance. To fully model the global correlation between the spatial and the angular information, we propose an Extended Spatial-Angular Interaction (ESAI) module to merge them, in which a simple and effective Transformer-based Spatial-Angular Interaction Attention (SAIA) block is also proposed for modeling long-range geometric correlations and making full use of the angular information. Furthermore, to improve the generalization performance of our network on real-world rainy scenes, we propose a novel semi-supervised learning framework for our MDeRainNet, which utilizes multi-level KL loss to bridge the domain gap between features of synthetic and real-world rain streaks and introduces colored-residue image guided contrastive regularization to reconstruct rain-free images. Extensive experiments conducted on synthetic and real-world LFIs demonstrate that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.

cs.CV↗