Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
Exploring efficient open-vocabulary segmentation in the remote sensing,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
IDCL adds density-based curriculum learning and density-core guidance to deep image clustering, claiming superior robustness, faster convergence, and flexibility on benchmark datasets.
GR-CoT improves remote sensing open-vocabulary segmentation by building category interpretation standards offline and using macro-scenario anchoring plus knowledge-driven synthesis online to create image-adaptive vocabularies.
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
SAM 3 can be applied training-free to remote sensing open-vocabulary segmentation and change detection by fusing its semantic and instance heads and filtering with presence scores.
citing papers explorer
-
Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
-
Deep Image Clustering Based on Curriculum Learning and Density Information
IDCL adds density-based curriculum learning and density-core guidance to deep image clustering, claiming superior robustness, faster convergence, and flexibility on benchmark datasets.
-
Geospatial-Reasoning-Driven Vocabulary-Agnostic Remote Sensing Semantic Segmentation
GR-CoT improves remote sensing open-vocabulary segmentation by building category interpretation standards offline and using macro-scenario anchoring plus knowledge-driven synthesis online to create image-adaptive vocabularies.
-
PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
-
SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images
SAM 3 can be applied training-free to remote sensing open-vocabulary segmentation and change detection by fusing its semantic and instance heads and filtering with presence scores.