OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation

arXiv:2604.08110v2 Announce Type: replace-cross Abstract: Training-free open-vocabulary semantic segmentation(TF-OVSS) has recently attracted attention for its ability to perform dense prediction by leveraging the pretrained knowledge of large vision and vision-language models, without requiring additional training. However, due to the limited input resolution of these pretrained encoders, existing TF-OVSS methods commonly adopt a sliding-window strategy that processes cropped sub-images indepen