Decoupling spatial basis refinement from low-rank channel mixing in convolutional layers yields better parameter-efficient fine-tuning for vision foundation models.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models
Decoupling spatial basis refinement from low-rank channel mixing in convolutional layers yields better parameter-efficient fine-tuning for vision foundation models.