2 papers
cs.CV2026
When Does Resolution Help a Frozen Backbone? Global Attention at Resolution Predicts Scalable Adaptation for Camouflaged and Marine Animal Segmentation
Tyler Rust, Chandra Kambhamettu
Adapting frozen vision foundation models to fine-grained segmentation now largely depends on backbone selection. Whether the backbone applies global attention to a high-resolution…
cs.CV2026
BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors
Tyler Rust, Dara McNally, Kyle O'Donnell +2
Building upon the SAM2 vision foundation model for downstream segmentation, this study introduces Boundary Enhanced Depth (BED)-SAM2. The SAM2 Hiera encoder architecture is modifie…