"this Is My Unicorn, Fluffy": Personalizing Frozen Vision-language Representations

Abstract

Large Vision & Language models pretrained on web-scale data provide representations that are invaluable for numerous V&L problems. However, it is unclear how they can be used for reasoning about user-specific visual concepts in unstructured language. This problem arises in multiple domains, from personalized image retrieval to personalized interaction with smart devices. We introduce a new learning setup called Personalized Vision & Language (PerVL) with two new benchmark datasets for retrieving and segmenting user-specific "personalized" concepts "in the wild". In PerVL, one should learn personalized concepts (1) independently of the downstream task (2) allowing a pretrained model to reason about them with free language, and (3) does not require personalized negative examples. We propose an architecture for solving PerVL that operates by extending the input vocabulary of a pretrained model with new word embeddings for the new personalized concepts. The model can then reason about them

Stats

• citations50
• S2 citations—
• github stars0
• HF likes0
• heat score12.81
• arxiv keycohen2022this

Related papers

• Meta-personalizing Vision-language Models To Find Named Instances In Video (2023)8.60
• Personalization Toolkit: Training Free Personalization Of Large Vision Language Models (2026)0.00
• Improving Personalized Search With Regularized Low-rank Parameter Updates (2025)0.00
• Infusing Fine-grained Visual Knowledge To Vision-language Models (2025)0.00
• Vilbert: Pretraining Task-agnostic Visiolinguistic Representations For Vision-and-language Tasks (2019)0.00
• Probvlm: Probabilistic Adapter For Frozen Vision-language Models (2023)13.41
• Vldeformer: Vision-language Decomposed Transformer For Fast Cross-modal Retrieval (2021)10.21
• Steerable Visual Representations (2026)0.00