arXiv subjects

Sumin Shen

Publications and source records attributed to Sumin Shen.

3 recordsLinked to original sources

arXiv2026

EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection

Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references. Despite recent advances, existing methods struggle with reference-target semantic alignment, explicit uncertainty modeling, and robust boundary preservation. To address these issues, we propose EviRCOD, an integrated framework consisting of three core components: (1) a Reference-Guided Deformable Encoder (RGDE) that employs hierarchical reference-driven modulation and multi-scale deformable aggregation to inject semantic priors and align cross-scale representations; (2) an Uncertainty-Aware Evidential Decoder (UAED) that incorporates Dirichlet evidence estimation into hierarchical decoding to model uncertainty and propagate confidence across scales; and (3) a Boundary-Aware Refinement Module (BARM) that selectively enhances ambiguous boundaries by exploiting low-level edge cues and prediction confidence. Experiments on the Ref-COD benchmark demonstrate that EviRCOD achieves state-of-the-art detection performance while providing well-calibrated uncertainty estimates. Code is available at: https://github.com/blueecoffee/EviRCOD.

cs.CV↗

arXiv2022

Clustering-based Imputation for Dropout Buyers in Large-scale Online Experimentation

In online experimentation, appropriate metrics (e.g., purchase) provide strong evidence to support hypotheses and enhance the decision-making process. However, incomplete metrics are frequently occurred in the online experimentation, making the available data to be much fewer than the planned online experiments (e.g., A/B testing). In this work, we introduce the concept of dropout buyers and categorize users with incomplete metric values into two groups: visitors and dropout buyers. For the analysis of incomplete metrics, we propose a clustering-based imputation method using $k$-nearest neighbors. Our proposed imputation method considers both the experiment-specific features and users' activities along their shopping paths, allowing different imputation values for different users. To facilitate efficient imputation of large-scale data sets in online experimentation, the proposed method uses a combination of stratification and clustering. The performance of the proposed method is compared to several conventional methods in both simulation studies and a real online experiment at eBay.

cs.LG↗

arXiv2019

Microstructure and Elastic Constants of Transition Metal Dichalcogenide Monolayers from Friction and Shear Force Microscopy

Optical and electrical properties of two-dimensional transition metal dichalcogenides (TMDCs) grown by chemical vapor deposition (CVD) are strongly determined by their microstructure. Consequently, the visualization of spatial structural variations is of paramount importance for future applications. Here we demonstrate how grain boundaries, crystal orientation, and strain fields can unambiguously be identified with combined lateral force microscopy (LFM) and transverse shear microscopy (TSM) for CVD-grown tungsten disulfide (WS2) monolayers, on length scales that are relevant for optoelectronic applications. Further, angle-dependent TSM measurements enable us to acquire the fourth-order elastic constants of monolayer WS2 experimentally. Our results facilitate high-throughput and nondestructive microstructure visualization of monolayer TMDCs, insights into their elastic properties, thus providing an accessible tool to support the development of advanced optoelectronic devices based on such two-dimensional semiconductors.

cond-mat.mtrl-sci↗