Learning Visual Representation with Synthetic Images and Topologically-defined Labels

Shizuo Kaji, Yohsuke Watanabe

Keywords: topology, persistent homology, self-supervised learning, synthetic image

TL;DR: We propose a new type of pretext task for self-supervised learning with synthetic images and mathematically-defined labels to incentivise learning global topological features of images

Abstract:

We propose a scheme for neural networks to learn visual representation with synthetic images and mathematically-defined labels that capture topological information. To verify that the model acquires a different visual representation than with the usual supervised learning with manually-defined labels, we show that the models pretrained with our scheme can be finetuned for image classification tasks to achieve an improved convergence compared to those trained from scratch.
Convolutional neural networks, built upon iterative local operations, are good at learning local features of the image, such as texture, whereas they tend to pay less attention to larger structures. Our method provides a simple way to encourage the model to learn global features through a specifically designed task based on topology. Furthermore, our method requires no real images nor manual labels; hence it sheds light on some of the lately concerned topics in computer vision, such as the cost and the fairness in data collection and annotation.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning