Timezone: »

 
An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?
Tyler Scott · Ting Liu · Michael Mozer · Andrew Gallagher
Event URL: https://openreview.net/forum?id=TbEzwuIs__ »
Recent research in clustering face embeddings has found that unsupervised, shallow, heuristic-based methods---including $k$-means and hierarchical agglomerative clustering---underperform supervised, deep, inductive methods. While the reported improvements are indeed impressive, experiments are mostly limited to face datasets, where the clustered embeddings are highly discriminative or well-separated by class (Recall@1 above 90% and often near ceiling), and the experimental methodology seemingly favors the deep methods. We conduct an empirical study of 14 clustering methods on two popular non-face datasets---Cars196 and Stanford Online Products---and obtain robust, but contentious findings. Notably, deep methods are surprisingly fragile for embeddings with more uncertainty, where they underperform the shallow, heuristic-based methods. We believe our benchmarks broaden the scope of supervised clustering methods beyond the face domain and can serve as a foundation on which these methods could be improved.

Author Information

Tyler Scott (University of Colorado, Boulder)
Ting Liu (Google Research)
Michael Mozer (Google Research, Brain Team)
Andrew Gallagher (Google)

More from the Same Authors