Shen, Yuming;
Shen, Ziyi;
Wang, Menghan;
Qin, Jie;
Torr, Philip;
Shao, Ling;
(2021)
You Never Cluster Alone.
In:
Advances in Neural Information Processing Systems 34 (NeurIPS 2021).
NeurIPS: Virtual.
Preview |
Text
NeurIPS-2021-you-never-cluster-alone-Paper.pdf - Accepted Version Download (2MB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | You Never Cluster Alone |
| Event: | 35th Conference on Neural Information Processing Systems (NeurIPS 2021). |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://proceedings.neurips.cc/paper/2021/hash/e96... |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10148476 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
