5 papers
Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification
Xinrui Zhou, Yuhao Huang, Haoran Dou +13
In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative au…
UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelation
Wei Zhuo, Zhiyue Tang, Wufeng Xue +3
Few-shot semantic segmentation has attracted growing interest for its ability to generalize to novel object categories using only a few annotated samples. To address data scarcity,…
Beyond Class Tokens: LLM-guided Dominant Property Mining for Few-shot Classification
Wei Zhuo, Runjie Luo, Wufeng Xue +1
Few-shot Learning (FSL), which endeavors to develop the generalization ability for recognizing novel classes using only a few images, faces significant challenges due to data scarc…
3D Heart Reconstruction from Sparse Pose-agnostic 2D Echocardiographic Slices
Zhurong Chen, Jinhua Chen, Wei Zhuo +2
Echocardiography (echo) plays an indispensable role in the clinical practice of heart diseases. However, ultrasound imaging typically provides only two-dimensional (2D) cross-secti…
EchoONE: Segmenting Multiple echocardiography Planes in One Model
Jiongtong Hu, Wei Zhuo, Jun Cheng +3
In clinical practice of echocardiography examinations, multiple planes containing the heart structures of different view are usually required in screening, diagnosis and treatment…