Searcharxiv⌕ Search

arXiv subjects

Fengshi Jing

Publications and source records attributed to Fengshi Jing.

3 recordsLinked to original sources

Honest confidence sets under experiment-level failure

An experiment-level failure replaces the joint observation law while preserving the target. We study honest confidence sets when a declared upper bound on failure probability equals the allowed noncoverage probability. For a Uniform support endpoint and a Gaussian mean on fixed compact parameter intervals, every honest deterministic procedure has full-range worst-case expected diameter under arbitrary or absolutely continuous joint failures. Independent randomisation gives sharp minimax risks of $(2+o(1))\log N/N$ for the endpoint in $[1,2]$ and $(2σ+o(1))(\log N/N)^{1/2}$ for the mean with known variance $σ^2$. A failure distribution shared by many targets forces average clean-state noncoverage to decrease with expected diameter. One-sided local Kullback--Leibler bounds then yield lower bounds with logarithmic factors. The endpoint experiment also has a sharp deterministic frontier as the remaining error budget vanishes. Under exchangeable failures without ties, observation order recovers both randomised benchmark rates deterministically. In a reference-calibrated roster, we derive the randomised minimax reliability rate. A prespecified reference reserve of logarithmic size permits deterministic attainment of the same order on a subclass whose conditionally independent reserved responses have probabilities bounded away from zero and one in every state.

stat.ME↗

Fundus Image-based Glaucoma Screening via Retinal Knowledge-Oriented Dynamic Multi-Level Feature Integration

While deep learning has advanced automated glaucoma screening via color fundus photography, existing purely data-driven models often overfit to confounding imaging artifacts and struggle to capture unpredictable pathological cues located beyond predefined anatomical boundaries. To address these limitations, we propose a retinal knowledge-oriented framework that synergizes dynamic multi-scale feature learning with domain-specific anatomical priors. The proposed architecture adopts a tri-branch structure to jointly model the global retinal context, the structural characteristics of the optic cup and disc, and dynamically cropped pathological regions. Specifically, we devise a Dynamic Window Mechanism (DWM) that adaptively discovers diagnostically informative patches via image-level supervision. Furthermore, we introduce a Knowledge-Enhanced Convolutional Block Attention Module (KE-CBAM) that explicitly incorporates retinal priors from a pre-trained foundation model RETFound to guide spatial attention, preventing the network from assigning spurious weights to irrelevant background noise. Extensive evaluations on the large-scale AIROGS dataset demonstrate that our method achieves a state-of-the-art AUC of $98.5\%$ and an accuracy of $94.6\%$. More importantly, the integration of anatomical priors effectively mitigates the inherent class imbalance, significantly improving the detection of referable glaucoma cases. Additional validations on the SMDG-19 benchmark further confirm its superior cross-domain generalization, indicating that our contribution provides a robust, interpretable, and scalable solution for real-world clinical glaucoma diagnosis. Our code is available at https://github.com/magiczhuo/Glaucoma-Detection

cs.CV↗

Knowledge-Enhanced Attentive Learning for Answer Selection in Community Question Answering Systems

In the community question answering (CQA) system, the answer selection task aims to identify the best answer for a specific question, and thus is playing a key role in enhancing the service quality through recommending appropriate answers for new questions. Recent advances in CQA answer selection focus on enhancing the performance by incorporating the community information, particularly the expertise (previous answers) and authority (position in the social network) of an answerer. However, existing approaches for incorporating such information are limited in (a) only considering either the expertise or the authority, but not both; (b) ignoring the domain knowledge to differentiate topics of previous answers; and (c) simply using the authority information to adjust the similarity score, instead of fully utilizing it in the process of measuring the similarity between segments of the question and the answer. We propose the Knowledge-enhanced Attentive Answer Selection (KAAS) model, which enhances the performance through (a) considering both the expertise and the authority of the answerer; (b) utilizing the human-labeled tags, the taxonomy of the tags, and the votes as the domain knowledge to infer the expertise of the answer; (c) using matrix decomposition of the social network (formed by following-relationship) to infer the authority of the answerer and incorporating such information in the process of evaluating the similarity between segments. Besides, for vertical community, we incorporate an external knowledge graph to capture more professional information for vertical CQA systems. Then we adopt the attention mechanism to integrate the analysis of the text of questions and answers and the aforementioned community information. Experiments with both vertical and general CQA sites demonstrate the superior performance of the proposed KAAS model.

cs.AI↗