KEC constructs hierarchical textual knowledge from LLMs to create knowledge-enhanced image features that improve clustering performance over baselines and zero-shot CLIP on 20 datasets.
Image clustering via the principle of rate reduction in the age of pretrained models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hierarchical Textual Knowledge for Enhanced Image Clustering
KEC constructs hierarchical textual knowledge from LLMs to create knowledge-enhanced image features that improve clustering performance over baselines and zero-shot CLIP on 20 datasets.