3 citations · 5 across the 9 of their papers we have counts for
9 papers
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…
Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation
Jinlong Li, Dong Zhao, Qi Zang +3
Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios with changing target distributions. Existing CTTA met…
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…
FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation
Dong Zhao, Jinlong Li, Shuang Wang +4
Vision Foundation Models (VFMs) excel in generalization due to large-scale pretraining, but fine-tuning them for Domain Generalized Semantic Segmentation (DGSS) while maintaining t…
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…
Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation
Dong Zhao, Shuang Wang, Qi Zang +3
We study source-free unsupervised domain adaptation (SFUDA) for semantic segmentation, which aims to adapt a source-trained model to the target domain without accessing the source…
Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation
Dong Zhao, Ruizhi Yang, Shuang Wang +5
Presently, self-training stands as a prevailing approach in cross-domain semantic segmentation, enhancing model efficacy by training with pixels assigned with reliable pseudo-label…
The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagery
Omid Ghorbanzadeh, Yonghao Xu, Hengwei Zhao +12
The scientific outcomes of the 2022 Landslide4Sense (L4S) competition organized by the Institute of Advanced Research in Artificial Intelligence (IARAI) are presented here. The obj…
More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation
Shuang Wang, Dong Zhao, Yi Li +5
Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation. Existing feature alignment methods for semantic s…