Discovering Multiple and Diverse Directions for Cognitive Image Properties
Not on the map. Why?
Abstract (arXiv)
Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained GANs. These directions enable controllable generation and support a variety of semantic editing operations. While previous work has focused on discovering a single direction that performs a desired editing operation such as zoom-in, limited work has been done on the discovery of multiple and diverse directions that can achieve the desired edit. In this work, we propose a novel framework that discovers multiple and diverse directions for a given property of interest. In particular, we focus on the manipulation of cognitive properties such as Memorability, Emotional Valence and Aesthetics. We show with extensive experiments that our method successfully manipulates these properties while producing diverse outputs. Our project page and source code can be found at http://catlab-team.github.io/latentcognitive.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 23 Feb 2022.
Builds on
30 of 37 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2017Mask R-CNNcited by 7,259
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
- 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
- 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
- 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
18 more
- 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
- 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
- 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
- 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
- 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
- 2018Moments in Time Dataset: one million videos for event understandingcited by 215
- 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
- 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 208
- 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
- 2019Image Processing Using Multi-Code GAN Priorcited by 185
- 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 122
- 2020Controlling generative models with continuous factors of variationscited by 93
- 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
- 2021Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigationcited by 53
- 2021LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directionscited by 52
- 2021WarpedGANSpace: Finding non-linear RBF paths in GAN latent spacecited by 48
- 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
- 2021Latent Transformations via NeuralODEs for GAN-based Image Editingcited by 11
Built on by
Not cited yet.