Exploring Unlabeled Faces for Novel Attribute Discovery
Hyojin Bahng, Sunghyo Chung, Seungjoo Yoo, Jaegul Choo
2020Year
5Top-tier citations
Abstract
Input Unpaired & unlabeled translation results (a) Ethnicity / Skin color (b) Hair color (c) Age / Facial hair (d) Additional results Figure 1 : Given raw, unlabeled data, our algorithm discovers novel facial attributes and performs high-quality multi-domain image translation. All results are based on newly-found attributes from our algorithm (e.g., a wide range of ethnicity, skin and hair color, age, facial hair, accessories, and makeup). We did not use any pre-defined attribute labels to generate the results.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers5
- Rethinking the Truly Unsupervised Image-to-Image TranslationKyungjune Baek, Yunjey Choi, Youngjung Uh, Jaejun Yoo et al.ICCV 2021 · 115 citations
- A Style-aware Discriminator for Controllable Image TranslationKunhee Kim, Sanghun Park, Eunyeong Jeon, Taehun Kim et al.CVPR 2022 · 31 citations
- MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with ResistanceSubin Kim, Hoonrae Kim, Jihyun Lee, Yejin Jeon et al.EMNLP 2025 · 6 citations
- Stay Positive: Non-Negative Image Synthesis for Augmented RealityKatie Luo, Guandao Yang, Wenqi Xian, Harald Haraldsson et al.CVPR 2021
- LANIT: Language-Driven Image-to-Image Translation for Unlabeled DataJihye Park, Sunwoo Kim, Soohyun Kim, Seokju Cho et al.CVPR 2023
Builds on2
Related papers
- RelGAN: Multi-Domain Image-to-Image Translation via Relative AttributesYu-Jing Lin, Po-Wei Wu, Che-Han Chang, Edward Y. Chang et al.ICCV 2019 · 158 citations
- Unpaired Multi-domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric MapZhenfeng Fan, Zhiheng Zhang, Shuang Yang, Chongyang Zhong et al.ICCV 2023 · 2 citations
- LOHO: Latent Optimization of Hairstyles via OrthogonalizationRohit Saha, Brendan Duke, Florian Shkurti, Graham W. Taylor et al.CVPR 2021
- Describe What to Change: A Text-guided Unsupervised Image-to-image Translation ApproachYahui Liu, Marco De Nadai, Deng Cai, Huayang Li et al.ACM MM 2020 · 58 citations
- MaskGAN: Towards Diverse and Interactive Facial Image ManipulationCheng-Han Lee, Ziwei Liu, Lingyun Wu, Ping LuoCVPR 2020
