TP-DRSeg: improving diabetic retinopathy lesion segmentation with explicit text-prompts assisted SAM

W Li, X **ong, P **a, L Ju, Z Ge - International Conference on Medical …, 2024 - Springer
Recent advances in large foundation models, such as the Segment Anything Model (SAM),
have demonstrated considerable promise across various tasks. Despite their progress …

Generalizing to unseen domains in diabetic retinopathy with disentangled representations

P **a, M Hu, F Tang, W Li, W Zheng, L Ju… - … Conference on Medical …, 2024 - Springer
Diabetic Retinopathy (DR), induced by diabetes, poses a significant risk of visual
impairment. Accurate and effective grading of DR aids in the treatment of this condition. Yet …

Diffusion model driven test-time image adaptation for robust skin lesion classification

M Hu, S Yan, P **a, F Tang, W Li, P Duan… - arxiv preprint arxiv …, 2024 - arxiv.org
Deep learning-based diagnostic systems have demonstrated potential in skin disease
diagnosis. However, their performance can easily degrade on test domains due to …

LMPT: prompt tuning with class-specific embedding loss for long-tailed multi-label visual recognition

P **a, D Xu, M Hu, L Ju, Z Ge - arxiv preprint arxiv:2305.04536, 2023 - arxiv.org
Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the
label co-occurrence and imbalanced data distribution. In this work, we propose a unified …

Hierarchical fine-grained visual classification leveraging consistent hierarchical knowledge

Y Liu, L Yang, Y Wang - Joint European Conference on Machine Learning …, 2024 - Springer
Hierarchical fine-grained visual classification assigns multi-granularity labels to each object,
forming a tree hierarchy. However, how to minimize the impact of coarse-grained …