Litcius/Paper detail

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

Oğuz Kaan Yüksel, Enis Simsar, Ezgi Gülperi Er, Pinar Yanardag

20212021 IEEE/CVF International Conference on Computer Vision (ICCV)58 citationsDOIOpen Access PDF

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.

Topics & Concepts

Computer scienceArtificial intelligenceGenerative grammarZoomMachine learningA priori and a posterioriUnsupervised learningRange (aeronautics)Supervised learningNatural language processingPattern recognition (psychology)Artificial neural networkEpistemologyComposite materialLens (geology)PhilosophyMaterials scienceEngineeringPetroleum engineeringGenerative Adversarial Networks and Image SynthesisImage Processing and 3D ReconstructionCell Image Analysis Techniques
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions | Litcius