Personalized Representation from Personalized Generation
Shobhita Sundaram, Julia Chae, Yonglong Tian, Sara Beery, Phillip Isola
2025Year
5Top-tier citations
Abstract
Learning personalized representations from limited real data. In this paper we explore whether and how synthetic data can be used to train a personalized representation. Given a few real images of an instance, we generate novel images and contrastively fine-tune a general-purpose pretrained model to learn a personalized representation, useful for diverse downstream tasks.
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
- Find your Needle: Small Object Image Retrieval via Multi-Object Attention OptimizationMichael Green, Matan Levy, Issar Tzachor, Dvir Samuel et al.NeurIPS 2025 · 1 citation
- Training-Free Personalization via Retrieval and Reasoning on FingerprintsDeepayan Das, Davide Talon, Yiming Wang, Massimiliano Mancini et al.ICCV 2025 · 1 citation
- Not All Birds Look The Same: Identity-Preserving Generation For BirdsAaron Sun, Oindrila Saha, Subhransu MajiCVPR 2026
- ID-Sim: An Identity-Focused Similarity MetricJulia Chae, Nick Kolkin, Jui-Hsien Wang, Richard Zhang et al.CVPR 2026
- Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?Tilemachos Aravanis, Vladan Stojnic, Bill Psomas, Nikos Komodakis et al.CVPR 2026
Builds on35
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- TransReID: Transformer-based Object Re-IdentificationShuting He, Hao Luo, Pichao Wang, Fan Wang et al.ICCV 2021 · 1,172 citations
- ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image GenerationYuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai et al.ICCV 2023 · 469 citations
Related papers
- Few-Shot Adversarial Learning of Realistic Neural Talking Head ModelsEgor Zakharov, Aliaksandra Shysheya, Egor Burkov, Victor S. LempitskyICCV 2019 · 687 citations
- Learning General-purpose Biomedical Volume Representations using Randomized SynthesisNeel Dey, Benjamin Billot, Hallee E. Wong, Clinton J. Wang et al.ICLR 2025 · 1 citation
- Is Synthetic Data from Generative Models Ready for Image Recognition?Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue et al.ICLR 2023 · 56 citations
- Optimal Positive Generation via Latent Transformation for Contrastive LearningYinqi Li, Hong Chang, Bingpeng Ma, Shiguang Shan et al.NeurIPS 2022 · 9 citations
- FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical LearningYulei Qin, Xingyu Chen, Chao Chen, Yunhang Shen et al.AAAI 2023 · 5 citations
