Noise-as-targets representation learning for cifar10. Implementation based on the paper "Unsupervised Learning by Predicting Noise" by Bojanowski and Joulin.
Hi, This isn't really an issue as such, more of a request. Could you possible share your loss curves. How the MSE loss varies with epoch number. Thanks in anticipation.
Hello, I have some questions about the application of this method. Can we apply this method to text address clustering? If yes, how define the input data?
Hi,
I implemented this repository. As such, I get a mlp test accuracy of 42%. By directly connecting the mlp to the convolutional features instead of the representation layer, I could push the mlp test accuracy to about 52 %.The paper claims better test accuracy on tougher datasets like ImageNet and Pascal VOC. Please share some tips on improving test accuracy and get the results claimed in the paper. My plan is to eventually to eventually use this as a pre-training for image segmentation