CRITICAL ANALYSIS OF SELF-SUPERVISION

Presented by

Maral Rasoolijaberi

Introduction

This paper evaluated the performance of state-of-the-art self-supervised methods on learning weights of convolutional neural networks (CNNs) and on a per-layer basis. Also, this paper aims to figure out whether current self-supervision techniques can learn deep features from only one image.

The main goal of self-supervised learning is to take advantage of vast amount of unlabeled data for training CNNs and finding a generalized image representation. In self-supervised learning, unlabeled data generate ground truth labels per se by pretext tasks such as rotation estimation. For example, we have a picture of a cat without the label "cat". We rotate the cat image by 90 degrees clockwise and the CNN is trained in a way that to find the rotation axis [3].

Previous Work

In recent literature, several papers addressed self-supervised learning methods and learning from a single sample.

A BiGAN [2], or Bidirectional GAN, is simply a generative adversarial network plus an encoder. The generator maps latent samples to generated data and the encoder performs as the opposite of the generator. After training BiGAN, the encoder has learned to generate a rich image representation. In RotNet method [3], images are rotated and the CNN learns to figure out the direction. DeepCluster [4] alternates k-means clustering to learn stable feature representations under several image transformations.

Method & Experiment

In this paper, BiGAN, RotNet and DeepCluster are employed for training AlexNet in a self-supervised manner. Also, to evaluate the impact of the size of the training set, they used ImageNet and a same-size dataset generated from one single image. Various methods of data augmentation including cropping, rotation, scaling, contrast changes, and adding noise, have been used to generate the mentioned artificial dataset from only one image. With the intention of measuring the quality of deep features, a linear classifier is trained on top of each convolutional layer of AlexNet to find whether features are linearly separable. Linear probes are a commonly used technique to inspect how much each of the layers learned. Note that the main purpose of CNNs is to reach a linearly separable representation for images. Next, they have compared the results of a million images in the ImageNet dataset with a million augmented imaged generated from a single image. The same experiment has been done using the CIFAR10/100 dataset.

Results

Figure 2 shows how well representations at each level are linearly separable. According to results, training the CNN with self-supervision methods can match the performance of fully supervised learning in the first two convolutional layers. It must be pointed out that only one single image with massive augmentation is utilized in this experiment.

Conclusion

This paper revealed that if a strong data-augmentation be employed, as little as a single image is sufficient for self-supervision techniques to learn the first few layers of popular CNNs. However, even the presence of millions of images are not enough for learning the deeper layers, and supervision might still be necessary. The results confirmed that the weights of the first layers of deep networks contain limited information about natural images. Accordingly, current unsupervised learning is only about augmentation, and we probably do not use the capacity of million images, yet.

References

[1] Y. Asano, C. Rupprecht, and A. Vedaldi, “A critical analysis of self-supervision, or what we can learn from a single image,” inInternational Conference on Learning Representations, 2019

[2] J. Donahue, P. Kr ̈ahenb ̈uhl, and T. Darrell, “Adversarial feature learning,”arXiv preprint arXiv:1605.09782, 2016.

[3] S. Gidaris, P. Singh, and N. Komodakis, “Unsupervised representation learning by predicting image rotations,”arXiv preprintarXiv:1803.07728, 2018

[4] M. Caron, P. Bojanowski, A. Joulin, and M. Douze, “Deep clustering for unsupervised learning of visual features,” inProceedings ofthe European Conference on Computer Vision (ECCV), 2018, pp. 132–149