arXiv subjects

Qiyang Yu

Publications and source records attributed to Qiyang Yu.

4 recordsLinked to original sources

arXiv2025

Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting

Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing multi-scale approaches alleviate this issue by integrating hierarchical or hybrid features; however, they rely on fixed patch sizes and introduce redundant computation. To address these limitations, we propose Granularity-driven Vision Transformer (Grc-ViT), a dynamic coarse-to-fine framework that adaptively adjusts visual granularity based on image complexity. It comprises two key stages: (1) Coarse Granularity Evaluation module, which assesses visual complexity using edge density, entropy, and frequency-domain cues to estimate suitable patch and window sizes; (2) Fine-grained Refinement module, which refines attention computation according to the selected granularity, enabling efficient and precise feature learning. Two learnable parameters, {\alpha} and \b{eta}, are optimized end-to-end to balance global reasoning and local perception. Comprehensive evaluations demonstrate that Grc-ViT enhances fine-grained discrimination while achieving a superior trade-off between accuracy and computational efficiency.

cs.CV↗

arXiv2025

Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation

Prompt-free image segmentation aims to generate accurate masks without manual guidance. Typical pre-trained models, notably Segmentation Anything Model (SAM), generate prompts directly at a single granularity level. However, this approach has two limitations: (1) Localizability, lacking mechanisms for autonomous region localization; (2) Scalability, limited fine-grained modeling at high resolution. To address these challenges, we introduce Granular Computing-driven SAM (Grc-SAM), a coarse-to-fine framework motivated by Granular Computing (GrC). First, the coarse stage adaptively extracts high-response regions from features to achieve precise foreground localization and reduce reliance on external prompts. Second, the fine stage applies finer patch partitioning with sparse local swin-style attention to enhance detail modeling and enable high-resolution segmentation. Third, refined masks are encoded as latent prompt embeddings for the SAM decoder, replacing handcrafted prompts with an automated reasoning process. By integrating multi-granularity attention, Grc-SAM bridges granular computing with vision transformers. Extensive experimental results demonstrate Grc-SAM outperforms baseline methods in both accuracy and scalability. It offers a unique granular computational perspective for prompt-free segmentation.

cs.CV↗

arXiv2025

Diffusion Index Forecasting with Tensor Data

In this paper, we consider diffusion index forecasting with both tensor and non-tensor predictors, where the tensor structure is preserved with a Canonical Polyadic (CP) tensor factor model. When the number of non-tensor predictors is small, we study the asymptotic properties of the least squares estimator in this tensor factor-augmented regression, allowing for factors with different strengths. We derive an analytical formula for prediction intervals that accounts for the estimation uncertainty of the latent factors. In addition, we propose a novel thresholding estimator for the high-dimensional covariance matrix that is robust to cross-sectional dependence. When the number of non-tensor predictors exceeds or diverges with the sample size, we introduce a multi-source factor-augmented sparse regression model and establish the consistency of the corresponding penalized estimator. Simulation studies validate our theoretical results and an empirical application to U.S. trade flows demonstrates the advantages of our approach over other popular methods in the literature.

stat.ME↗

arXiv2024

Estimation and Inference for CP Tensor Factor Models

High-dimensional tensor-valued data have recently gained attention from researchers in economics and finance. We consider the estimation and inference of high-dimensional tensor factor models, where each dimension of the tensor diverges. Our focus is on a factor model that admits CP-type tensor decomposition, which allows for non-orthogonal loading vectors. Based on the contemporary covariance matrix, we propose an iterative simultaneous projection estimation method. Our estimator is robust to weak dependence among factors and weak correlation across different dimensions in the idiosyncratic shocks. We establish an inferential theory, demonstrating both consistency and asymptotic normality under relaxed assumptions. Within a unified framework, we consider two eigenvalue ratio-based estimators for the number of factors in a tensor factor model and justify their consistency. Simulation studies confirm the theoretical results and an empirical application to sorted portfolios reveals three important factors: a market factor, a long-short factor, and a volatility factor.

stat.ME↗