LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions

Oğuz Kaan Yüksel, Enis Simsar, Ezgi Gülperi Er, Pinar Yanardag; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 14263-14272

Abstract


Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of semantic editing operations, such as zoom or rotation. The discovery of such directions is often done in a supervised or semi-supervised manner and requires manual annotations which limits their use in practice. In comparison, unsupervised discovery allows finding subtle directions that are difficult to detect a priori. In this work, we propose a contrastive learning-based approach to discover semantic directions in the latent space of pre-trained GANs in a self-supervised manner. Our approach finds semantically meaningful dimensions compatible with state-of-the-art methods.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Yuksel_2021_ICCV, author = {Y\"uksel, O\u{g}uz Kaan and Simsar, Enis and Er, Ezgi G\"ulperi and Yanardag, Pinar}, title = {LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {14263-14272} }