7 papers
Language as an Anchor: Preserving Relative Visual Geometry for Domain Incremental Learning
Shuyi Geng, Tao Zhou, Yi Zhou
A key challenge in Domain Incremental Learning (DIL) is to continually learn under shifting distributions while preserving knowledge from previous domains. Existing methods face a…
Text-driven Multiplanar Visual Interaction for Semi-supervised Medical Image Segmentation
Kaiwen Huang, Yi Zhou, Huazhu Fu +3
Semi-supervised medical image segmentation is a crucial technique for alleviating the high cost of data annotation. When labeled data is limited, textual information can provide ad…
Continual Retinal Vision-Language Pre-training upon Incremental Imaging Modalities
Yuang Yao, Ruiqi Wu, Yi Zhou +1
Traditional fundus image analysis models focus on single-modal tasks, ignoring fundus modality complementarity, which limits their versatility. Recently, retinal foundation models…
Universal Incremental Learning: Mitigating Confusion from Inter- and Intra-task Distribution Randomness
Sheng Luo, Yi Zhou, Tao Zhou
Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task typ…
MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining
Ruiqi Wu, Na Su, Chenran Zhang +10
Vision-language pretraining (VLP) has been investigated to generalize across diverse downstream tasks for fundus image analysis. Although recent methods showcase promising achievem…
Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image Segmentation
Kaiwen Huang, Tao Zhou, Huazhu Fu +4
The limited availability of labeled data has driven advancements in semi-supervised learning for medical image segmentation. Modern large-scale models tailored for general segmenta…