CRITICAL ANALYSIS OF SELF-SUPERVISION: Difference between revisions
(→Method) |
|||
| Line 7: | Line 7: | ||
== Method == | == Method == | ||
In the self-supervision methods, the hypothesis function without target labels is defined. | |||
Let <math> x <math> be a sample from the unlabeled dataset. The weights of the CNN are learnt in a way that minimizes <math> |h(x)-x| <math> where $h(x)$ is a hypothesis function, i.e. BiGAN, RoTNet and DeepCluster. | |||
AlexNet as CNN, and various methods of data augmentation including cropping, rotation, scaling, contrast changes, and adding noise, have been used in this paper. | |||
To measure the quality of features, they train a linear classifier on top of each convolutional layer of AlexNet to find whether features are linearly separable. In general, the main purpose of CNN is to reach a linearly separable representation for images. | |||
Next, they compared the results of a million images in the ImageNet dataset with a million augmented imaged generated from a single image. | |||
== results == | == results == | ||
Revision as of 18:27, 26 November 2020
Presented by
Maral Rasoolijaberi
Introduction
Previous Work
Method
In the self-supervision methods, the hypothesis function without target labels is defined. Let <math> x <math> be a sample from the unlabeled dataset. The weights of the CNN are learnt in a way that minimizes <math> |h(x)-x| <math> where $h(x)$ is a hypothesis function, i.e. BiGAN, RoTNet and DeepCluster. AlexNet as CNN, and various methods of data augmentation including cropping, rotation, scaling, contrast changes, and adding noise, have been used in this paper. To measure the quality of features, they train a linear classifier on top of each convolutional layer of AlexNet to find whether features are linearly separable. In general, the main purpose of CNN is to reach a linearly separable representation for images. Next, they compared the results of a million images in the ImageNet dataset with a million augmented imaged generated from a single image.