• 1.Papers[]

• 2.Paper Reading Notes

• Temporal ensembling for semi-supervised learning. Samuli Laine and Timo Aila. paper_url

• Mean teacher: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. paper_url

• VAT: Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning. paper_url

• fast SWA: There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average. paper_url

• ICT by Bengio: Interpolation Consistency Training for Semi-Supervised Learning. paper_url

• MixMatch by Ian Goodfellow: Interpolation Consistency Training for Semi-Supervised Learning. paper_url

• Temporal ensembling for semi-supervised learning

to do

• Mean teacher: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.

to do

• VAT: Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning.

to do

• fast SWA: There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average.

to do

• ICT by Bengio: Interpolation Consistency Training for Semi-Supervised Learning.

to do

• MixMatch by Ian Goodfellow: Interpolation Consistency Training for Semi-Supervised Learning.

to do