CoAt-CBM improves fine-grained concept alignment in CBMs by using adaptive visual queries per concept and a contrastive loss that respects relative concept importance instead of independent BCE.
The caltech-ucsd birds-200-2011 dataset
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
SigLino distills SigLIP2 and DINOv3 into efficient vision models via asymmetric relation-knowledge distillation, token-balanced batching, and hierarchical data sampling on a new 200M-image corpus, yielding better transfer to grounding VLMs than training from scratch.
citing papers explorer
-
Concept-wise Attention for Fine-grained Concept Bottleneck Models
CoAt-CBM improves fine-grained concept alignment in CBMs by using adaptive visual queries per concept and a contrastive loss that respects relative concept importance instead of independent BCE.
-
SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models
SigLino distills SigLIP2 and DINOv3 into efficient vision models via asymmetric relation-knowledge distillation, token-balanced batching, and hierarchical data sampling on a new 200M-image corpus, yielding better transfer to grounding VLMs than training from scratch.