Compara mètodes
Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.
| Aprenentatge per transferència auto-supervisat× | Aprenentatge mètric× | |
|---|---|---|
| Camp | Aprenentatge automàtic | Aprenentatge automàtic |
| Família | Machine learning | Machine learning |
| Any d'origen≠ | 2018–2020 (modern consolidation) | 2003 (foundational); refined 2009 (LMNN) |
| Autor original≠ | LeCun, Y. (concept); Devlin et al. (BERT, NLP); Chen et al. (SimCLR, vision) | Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y. |
| Tipus≠ | Learning paradigm (self-supervised pre-training + fine-tuning) | Representation learning / supervised distance optimization |
| Font seminal≠ | Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607. link ↗ | Xing, E. P., Jordan, M. I., Russell, S., & Ng, A. Y. (2003). Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems (NIPS), 16, 505–512. link ↗ |
| Àlies | self-supervised pre-training, SSL-based transfer learning, representation transfer from self-supervised models, contrastive pre-training with transfer | Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance |
| Relacionats≠ | 6 | 5 |
| Resum≠ | Self-supervised transfer learning combines two powerful paradigms: a model first learns rich representations from unlabeled data using self-supervised pretext tasks, then those learned representations are transferred and fine-tuned on a downstream task with limited labeled data. This approach underlies landmark systems such as BERT in NLP and SimCLR and DINO in computer vision, dramatically reducing labeled-data requirements across many domains. | Metric learning is a machine-learning framework that trains a distance or similarity function from data so that semantically similar examples end up close together in the learned space while dissimilar examples are pushed apart. Unlike fixed distances such as Euclidean, the learned metric adapts to the structure of the task, making downstream classifiers, clusterers, and retrieval systems significantly more accurate. |
| ScholarGateConjunt de dades ↗ |
|
|