Abstract
Here's a trimmed version under 1920 characters: Open-vocabulary segmentation models such as SAM3 achieve strong performance through concept-level text prompting, yet degrade when the target class is visually underrepresented in pretraining data or when its appearance departs from canonical depictions. Text prompts provide no spatial signal to resolve such ambiguity. We present SegRAG, a training-free retrieval-augmented segmentation framework that grounds SAM3 with spatially precise, class-specific point prompts derived from a curated DINOv3 feature bank. During an offline stage, patch-level descriptors are extracted from annotated reference images using a frozen DINOv3 ViT-L/16 backbone and filtered by Intra-Class Cohesion Distillation (ICCD), retaining only prototypes that reliably retrieve within-class foreground. At inference, Topographic Similarity Grounding (TSG) computes a cosine-similarity landscape between the query image and retrieved prototypes, identifies spatially coherent high-confidence regions via connected-component analysis, and extracts peak locations through non-maximum suppression. These point prompts are delivered to SAM3 alongside the class-name text in a single joint grounding pass, enabling the mask decoder to resolve semantic intent and spatial evidence together. SegRAG requires no task-specific training and no synthetic data. On four open-vocabulary benchmarks it achieves consistent gains over the SAM3 text-only baseline, with improvements of up to +3.92 mIoU on LVIS. On AgML agricultural benchmarks representing a zero-shot domain transfer setting, it raises mean IoU from 25.27 to 59.24 (+33.97) and recovers individual classes from zero to over 95 mIoU. Ablation studies confirm that ICCD, TSG, and joint prompting each contribute independently and compound when combined. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.17630
