Selected work

Representative Papers

Deep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors

Sep 24, 2026

This study addresses the challenge that assessing glaucoma progression rates typically requires multiple visual field tests over years, hindering the rapid identification of high-risk patients. We propose GLAM, a model that leverages longitudinal Humphrey visual field data and clinical features via an attention-based fusion mechanism to predict progression rates while quantifying aleatoric uncertainty. The key innovation lies in achieving performance comparable to multimodal approaches using only routine unimodal visual field data, thereby substantially shortening the assessment period. Experimental results demonstrate that GLAM predicts mean deviation (MD) progression rates with a mean absolute error of 0.139 dB/year (R²=0.927), reducing the error by 73.5% compared to baselines. Furthermore, the model attains an AUC of 0.990 for detecting fast progressors, enabling highly accurate and cost-effective early screening.

0 citationsRead paper

Spatial frequency information fusion network for few-shot learning

Jun 23, 2025

To address overfitting and poor generalization caused by data scarcity in few-shot image classification, this paper proposes SFIFNet—a novel network that explicitly fuses frequency-domain and spatial-domain information during data preprocessing for the first time. Methodologically, SFIFNet leverages frequency transforms (e.g., DCT or FFT) to extract global texture and structural priors, integrates them with multi-scale spatial features via a lightweight deep neural architecture, and further enhances robustness through conventional data augmentation. Its key contribution lies in breaking the prevailing reliance on spatial-domain representations alone, systematically exploiting discriminative and complementary features encoded in the frequency domain. Extensive experiments on standard few-shot benchmarks—including Mini-ImageNet and CUB—demonstrate that SFIFNet achieves significant improvements in classification accuracy (average gain of +2.3%) and superior cross-domain generalization capability.

0 citationsRead paper

Recent publications

Latest Papers

Deep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors

Sep 24, 2026

This study addresses the challenge that assessing glaucoma progression rates typically requires multiple visual field tests over years, hindering the rapid identification of high-risk patients. We propose GLAM, a model that leverages longitudinal Humphrey visual field data and clinical features via an attention-based fusion mechanism to predict progression rates while quantifying aleatoric uncertainty. The key innovation lies in achieving performance comparable to multimodal approaches using only routine unimodal visual field data, thereby substantially shortening the assessment period. Experimental results demonstrate that GLAM predicts mean deviation (MD) progression rates with a mean absolute error of 0.139 dB/year (R²=0.927), reducing the error by 73.5% compared to baselines. Furthermore, the model attains an AUC of 0.990 for detecting fast progressors, enabling highly accurate and cost-effective early screening.

0 citationsRead paper

Spatial frequency information fusion network for few-shot learning

Jun 23, 2025

To address overfitting and poor generalization caused by data scarcity in few-shot image classification, this paper proposes SFIFNet—a novel network that explicitly fuses frequency-domain and spatial-domain information during data preprocessing for the first time. Methodologically, SFIFNet leverages frequency transforms (e.g., DCT or FFT) to extract global texture and structural priors, integrates them with multi-scale spatial features via a lightweight deep neural architecture, and further enhances robustness through conventional data augmentation. Its key contribution lies in breaking the prevailing reliance on spatial-domain representations alone, systematically exploiting discriminative and complementary features encoded in the frequency domain. Extensive experiments on standard few-shot benchmarks—including Mini-ImageNet and CUB—demonstrate that SFIFNet achieves significant improvements in classification accuracy (average gain of +2.3%) and superior cross-domain generalization capability.

0 citationsRead paper