GSEC uses MLLM-generated semantic descriptions and a bi-layer ensemble (BatchEnsemble inner layer plus alignment outer layer) to reduce bias and variance, outperforming 18 prior methods on six image clustering benchmarks.
Deep clustering for unsupervised learning of visual features
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
-
Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering
GSEC uses MLLM-generated semantic descriptions and a bi-layer ensemble (BatchEnsemble inner layer plus alignment outer layer) to reduce bias and variance, outperforming 18 prior methods on six image clustering benchmarks.