Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
Abstract: While CLIP has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatialinvariant semantic features ...
Abstract: Referring remote sensing image segmentation (RSRIS) aims to achieve target-oriented, fine-grained understanding of geospatial information by leveraging both visual and linguistic modalities.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results