BMCR uses RL to adaptively compose modules from CNN and ViT backbones with an OT alignment interface, reporting mAP gains of up to 2.5 points on DOTA and DIOR-R datasets.
Conformer: Local features coupling global representations for visual recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BMCR: Adaptive Backbone Module Composition via Reinforcement Learning for Remote Sensing Object Detection
BMCR uses RL to adaptively compose modules from CNN and ViT backbones with an OT alignment interface, reporting mAP gains of up to 2.5 points on DOTA and DIOR-R datasets.