Clustering and Attention
Tim raises an intriguing question about the similarities between clustering assignments and attention mechanisms, suggesting a potential for hierarchical transformations in clustering. Mathilde acknowledges the resemblance but admits she hasn't explored this area yet, noting her current focus as a second-year PhD student. The conversation hints at exciting possibilities for future research in the intersection of clustering and transformer architectures.In this clip
From this podcast

Machine Learning Street Talk (MLST)
SWaV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (Mathilde Caron)
Related Questions