Timezone: »

You Never Cluster Alone
Yuming Shen · Ziyi Shen · Menghan Wang · Jie Qin · Philip Torr · Ling Shao

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @

Recent advances in self-supervised learning with instance-level contrastive objectives facilitate unsupervised clustering. However, a standalone datum is not perceiving the context of the holistic cluster, and may undergo sub-optimal assignment. In this paper, we extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation that encodes the context of each data group. Contrastive learning with this representation then rewards the assignment of each datum. To implement this vision, we propose twin-contrast clustering (TCC). We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. On one hand, with the corresponding assignment variables being the weight, a weighted aggregation along the data points implements the set representation of a cluster. We further propose heuristic cluster augmentation equivalents to enable cluster-level contrastive learning. On the other hand, we derive the evidence lower-bound of the instance-level contrastive objective with the assignments. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps. Extensive experiments show that TCC outperforms the state-of-the-art on benchmarked datasets.

Author Information

Yuming Shen (University of Oxford)
Ziyi Shen (Beijing Institute of Technology)
Menghan Wang (eBay)
Jie Qin (Inception Institute of Artificial Intelligence)
Philip Torr (University of Oxford)
Ling Shao (Inception Institute of Artificial Intelligence)

More from the Same Authors