8 papers
Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation
Lingrui Li, Nan Pu, Dong Zhao +4
Test-time adaptation (TTA) aims to mitigate distribution shifts by adapting models with unlabeled target data at inference time. While TTA with vision-language models (VLMs) has sh…
Open-Vocabulary Domain Generalization in Urban-Scene Segmentation
Dong Zhao, Qi Zang, Nan Pu +3
Domain Generalization in Semantic Segmentation (DG-SS) aims to enable segmentation models to perform robustly in unseen environments. However, conventional DG-SS methods are restri…
Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation
Chonghua Lv, Dong Zhao, Shuang Wang +4
Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while negle…
Lightweight Adapter Learning for More Generalized Remote Sensing Change Detection
Dou Quan, Rufan Zhou, Shuang Wang +4
Deep learning methods have shown promising performances in remote sensing image change detection (CD). However, existing methods usually train a dataset-specific deep network for e…
Generalization-aware Remote Sensing Change Detection via Domain-agnostic Learning
Qi Zang, Shuang Wang, Dong Zhao +3
Change detection has essential significance for the region's development, in which pseudo-changes between bitemporal images induced by imaging environmental factors are key challen…
ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model
Qi Zang, Jiayi Yang, Shuang Wang +3
Data-driven deep learning models have enabled tremendous progress in change detection (CD) with the support of pixel-level annotations. However, collecting diverse data and manuall…