GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation

arXiv:2608.07405v1 Announce Type: cross Abstract: Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometric errors that are amplified during distillation. This paper presents GeoDistill-Refine, a two-stage framework that transfers offline SAM 3 pseudo-masks to a compact segmentation network. Six fixed prompts are fused by an unweighted 50% vote to stabilize the teacher output. The student first learns the foreground silhouette and is then refined with signed-distance-field, skeleton, and area objectives derived from the pseudo-mask. A sample-level gate, computed from prompt agreement, the valid-prompt ratio, and pseudo-mask area plausibility, reduces the influence of unreliable pseudo-geometry. On the SpaceSense-Bench HJM lockbox set, GeoDistill-Refine improves Image IoU and Boundary F1 by 0.0456 and 0.1380, respectively, over a plain pseudo-label student. External evaluations on the SPEED+ Lightbox and Sunlamp domains and on TANGO show competitive regional overlap together with gains in boundary quality or foreground precision. The deployed TinyUNet contains 0.263 M parameters and requires approximately 1.1 ms per image on an RTX 4090; SAM 3 pseudo-mask construction and the auxiliary geometry branches are used only during training.

Related

• Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks
• Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing
• Coarse-to-Fine Domain Incremental Learning with Attentive Distillation for Mining Footprint Segmentation in Multispectral Imagery

Source: arXiv cs.AI | 2026-08-10