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

arXiv: https://arxiv.org/abs/2104.00820 · HTML: https://mlsanity.com/paper/2104.00820/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 2 Apr 2021.

## Builds on (most cited first, 29 of 29)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1710.10916/) (2017)
- [DeepFakes: a New Threat to Face Recognition? Assessment and Detection](https://mlsanity.com/paper/1812.08685/) (2018)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset](https://mlsanity.com/paper/1904.01538/) (2019)
- [Controlling generative models with continuous factors of variations](https://mlsanity.com/paper/2001.10238/) (2020)
- [Single Image Deraining: A Comprehensive Benchmark Analysis](https://mlsanity.com/paper/1903.08558/) (2019)
- [Learned Image Downscaling for Upscaling using Content Adaptive Resampler](https://mlsanity.com/paper/1907.12904/) (2019)
- [Navigating the GAN Parameter Space for Semantic Image Editing](https://mlsanity.com/paper/2011.13786/) (2020)
- [GAN "Steerability" without optimization](https://mlsanity.com/paper/2012.05328/) (2020)

## Built on by (most cited first, 30 of 52)

- [Diffusion Models already have a Semantic Latent Space](https://mlsanity.com/paper/2210.10960/) (2022)
- [High-Fidelity GAN Inversion for Image Attribute Editing](https://mlsanity.com/paper/2109.06590/) (2021)
- [Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry](https://mlsanity.com/paper/2307.12868/) (2023)
- [HyperInverter: Improving StyleGAN Inversion via Hypernetwork](https://mlsanity.com/paper/2112.00719/) (2021)
- [NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models](https://mlsanity.com/paper/2312.05390/) (2023)
- [3D GAN Inversion with Pose Optimization](https://mlsanity.com/paper/2210.07301/) (2022)
- [StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation](https://mlsanity.com/paper/2112.08493/) (2021)
- [Style Transformer for Image Inversion and Editing](https://mlsanity.com/paper/2203.07932/) (2022)
- [Text and Image Guided 3D Avatar Generation and Manipulation](https://mlsanity.com/paper/2202.06079/) (2022)
- [Temporally Consistent Semantic Video Editing](https://mlsanity.com/paper/2206.10590/) (2022)
- [User-Controllable Latent Transformer for StyleGAN Image Layout Editing](https://mlsanity.com/paper/2208.12408/) (2022)
- [Unsupervised Discovery of Semantic Latent Directions in Diffusion Models](https://mlsanity.com/paper/2302.12469/) (2023)
- [Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Exploration](https://mlsanity.com/paper/2207.09855/) (2022)
- [FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations](https://mlsanity.com/paper/2202.06240/) (2022)
- [Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint](https://mlsanity.com/paper/2211.11448/) (2022)
- [Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation](https://mlsanity.com/paper/2304.11829/) (2023)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [A Survey on Deep Generative 3D-aware Image Synthesis](https://mlsanity.com/paper/2210.14267/) (2022)
- [UnGANable: Defending Against GAN-based Face Manipulation](https://mlsanity.com/paper/2210.00957/) (2022)
- [LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis](https://mlsanity.com/paper/2301.04604/) (2023)
- [Deep Bregman Divergence for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2109.07455/) (2021)
- [RIGID: Recurrent GAN Inversion and Editing of Real Face Videos](https://mlsanity.com/paper/2308.06097/) (2023)
- [IA-FaceS: A Bidirectional Method for Semantic Face Editing](https://mlsanity.com/paper/2203.13097/) (2022)
- [Hierarchical Semantic Regularization of Latent Spaces in StyleGANs](https://mlsanity.com/paper/2208.03764/) (2022)
- [End-to-End Visual Editing with a Generatively Pre-Trained Artist](https://mlsanity.com/paper/2205.01668/) (2022)
- [FurryGAN: High Quality Foreground-aware Image Synthesis](https://mlsanity.com/paper/2208.10422/) (2022)
- [Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models](https://mlsanity.com/paper/2310.09912/) (2023)
- [Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models](https://mlsanity.com/paper/2403.19645/) (2024)
- [LatentSwap3D: Semantic Edits on 3D Image GANs](https://mlsanity.com/paper/2212.01381/) (2022)
- [Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs](https://mlsanity.com/paper/2203.08516/) (2022)

## Abstract (arXiv)

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 comparable with state-of-the-art methods.