Search Results for author:
Found 3 papers, 3 papers with code
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
CLIP embeddings have demonstrated remarkable performance across a wide range of computer vision tasks.
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
This strategy naturally combines the ease of use of post hoc explanations with the faithfulness of inherently interpretable models.
Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?
CompMap first asks a VL model to generate primitive concept activations with text prompts, and then learns to construct a composition model that maps the primitive concept activations (e. g. the likelihood of black tail or red wing) to composite concepts (e. g. a red-winged blackbird).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
