Machine learningMachine learning
Self-supervised DBSCAN
Self-supervised DBSCAN is a two-stage unsupervised pipeline that first trains a neural encoder on a pretext task — such as contrastive learning or masked reconstruction — to produce compact, semantically meaningful embeddings from unlabeled data, and then applies DBSCAN in the resulting embedding space to discover arbitrarily shaped clusters without requiring any class labels.
Open in MethodMindSoonVideoSoon
Read the full method
Members only
Sign inSign in with a free account to read this section.
Sources
- Ester, M., Kriegel, H.-P., Sander, J., & Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining (KDD-96), pp. 226–231. AAAI Press. link ↗
- Zhan, X., Liu, Z., Luo, P., Tang, X., & Loy, C. C. (2018). Rethinking deep neural network training for face recognition: A geometric approach. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2045–2054. link ↗