Paper issue: don't understand the proxy tasks' function?

gustavla / self-supervision

Training and evaluating self-supervised deep neural networks

BSD 3-Clause "New" or "Revised" License

29 stars 6 forks source link

Paper issue: don't understand the proxy tasks' function? #8

Open 2000222 opened 5 years ago

2000222 commented 5 years ago

So colorization as a proxy task in self-supervised learning just means that we pretrained the vgg16 or ResNet network for image colorization, and then transfer the weights in the pretrained model to the downstream task? What about features that we get?