SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.
IEEE Transactions on Image Processing34, 8271–8284 (2025) arXiv:2411.15869 [cs.CV]
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5verdicts
UNVERDICTED 5representative citing papers
OV-Stitcher improves training-free open-vocabulary semantic segmentation by stitching sub-image features to enable global attention in the final encoder block, raising mIoU from 48.7 to 50.7 across eight benchmarks.
RADSeg adapts the RADIO model with targeted enhancements to deliver 6-30% higher mIoU in zero-shot OVSS while using 2.5x fewer parameters and running 3.95x faster than prior large-model combinations.
The approach uses the analytic solution of distribution discrepancy consistency within categories as semantic maps, eliminating training and model-specific modulation while claiming state-of-the-art results on eight benchmarks.
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
-
SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation
SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.
-
OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation
OV-Stitcher improves training-free open-vocabulary semantic segmentation by stitching sub-image features to enable global attention in the final encoder block, raising mIoU from 48.7 to 50.7 across eight benchmarks.
-
RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models
RADSeg adapts the RADIO model with targeted enhancements to deliver 6-30% higher mIoU in zero-shot OVSS while using 2.5x fewer parameters and running 3.95x faster than prior large-model combinations.
-
Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
The approach uses the analytic solution of distribution discrepancy consistency within categories as semantic maps, eliminating training and model-specific modulation while claiming state-of-the-art results on eight benchmarks.
-
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.