UNC-biag
UNC-biag
Research
People
Publications
Software
Hall of Fame
Contact
Light
Dark
Automatic
contrastive learning
Dissecting Supervised Constrastive Learning
Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However, recent works show that one can directly …
Cite
×