OVRSISBenchV2 expands open-vocabulary remote-sensing segmentation evaluation to 170K images and 128 categories, and Pi-Seg uses positive-incentive noise to improve transfer on that harder benchmark.
Annotation-free open-vocabulary segmentation for remote-sensing images
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
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.
ProC-SAM3 builds a curated per-dataset prompt pool with an MLLM, caches text embeddings, and fuses SAM 3 mask outputs through a presence gate, reaching 56.1% average mIoU on eight remote-sensing benchmarks.
citing papers explorer
-
Towards Realistic Open-Vocabulary Remote Sensing Segmentation: Benchmark and Baseline
OVRSISBenchV2 expands open-vocabulary remote-sensing segmentation evaluation to 170K images and 128 categories, and Pi-Seg uses positive-incentive noise to improve transfer on that harder benchmark.
-
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.
-
Prompt-Calibrated SAM 3 for Open-Vocabulary Remote Sensing Semantic Segmentation
ProC-SAM3 builds a curated per-dataset prompt pool with an MLLM, caches text embeddings, and fuses SAM 3 mask outputs through a presence gate, reaching 56.1% average mIoU on eight remote-sensing benchmarks.