MMRL++ inserts shared, learnable representation tokens into the upper layers of CLIP's image and text encoders and uses low-rank shared aligners, achieving state-of-the-art base-to-novel harmonic mean accuracy on 11 datasets with 0.813M trainable parameters.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models
MMRL++ inserts shared, learnable representation tokens into the upper layers of CLIP's image and text encoders and uses low-rank shared aligners, achieving state-of-the-art base-to-novel harmonic mean accuracy on 11 datasets with 0.813M trainable parameters.