SLiCS learns group-structured non-negative dictionaries that disentangle dense image embeddings into concept components, improving concept-filtered retrieval and enabling image-to-prompt generation.
Multidimensional independent component analysis
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
-
Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)
SLiCS learns group-structured non-negative dictionaries that disentangle dense image embeddings into concept components, improving concept-filtered retrieval and enabling image-to-prompt generation.