paper-with-me

홈 › Papers

Improving Personalized Search with Regularized Low-Rank Parameter Updates

2025-06-11 · CVPR 2025 1 · Fiona Ryan, Josef Sivic, Fabian Caba Heilbron, Judy Hoffman, James M. Rehg, Bryan Russell

Personalized vision-language retrieval seeks to recognize new concepts (e.g. "my dog Fido") from only a few examples. This task is challenging because it requires not only learning a new concept from a few images, but also integrating the personal and general knowledge together to recognize the concept in different contexts. In this paper, we show how to effectively adapt the internal representation of a vision-language dual encoder model for personalized vision-language retrieval. We find that regularized low-rank adaption of a small set of parameters in the language encoder's final layer serves as a highly effective alternative to textual inversion for recognizing the personal concept while preserving general knowledge. Additionally, we explore strategies for combining parameters of multiple learned personal concepts, finding that parameter addition is effective. To evaluate how well general knowledge is preserved in a finetuned representation, we introduce a metric that measures image retrieval accuracy based on captions generated by a vision language model (VLM). Our approach achieves state-of-the-art accuracy on two benchmarks for personalized image retrieval with natural language queries - DeepFashion2 and ConCon-Chi - outperforming the prior art by 4%-22% on personal retrievals.

📄 PDF Abstract BibTeX arXiv:2506.10182

Code (1)

adobe-research/polar-vl 공식 구현 pytorch

Tasks

General KnowledgeImage RetrievalNatural Language QueriesRetrieval

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at Taobao

2026-03-24 · Zhi Sun, Wenming Zhang, Yi Wei, Liren Yu 외 arxiv

Large Language Models (LLMs) are equipped with profound semantic knowledge, making them a natural choice for injecting semantic generalization into personalized search systems. However, in practice we find that directly …

Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement

2026-07-30 · Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell, Yanrong Chen 외 arxiv

Personalized image enhancement should reflect individual aesthetic taste, yet learning such preferences commonly depends on private photos and ratings that are unsuitable for centralized collection. The task must infer p…

Image Enhancement

Fusion of Global and Local Knowledge for Personalized Federated Learning

2023-02-21 · Tiansheng Huang, Li Shen, Yan Sun, Weiwei Lin 외

Personalized federated learning, as a variant of federated learning, trains customized models for clients using their heterogeneously distributed data. However, it is still inconclusive about how to design personalized m…

Federated LearningPersonalized Federated Learning

Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

2026-08-12 · Mirko Konstantin, Stefan Zachow, Anirban Mukhopadhyay arxiv

Federated learning (FL) enables collaborative model training across distributed clients while keeping data local. A central challenge is determining which client updates are beneficial for aggregation with respect to eac…

Federated Learning

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

2026-05-08 · Omatharv Bharat Vaidya, Connor T. Jerzak, Nhat Ho, Chandrajit Bajaj arxiv

We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficiency by restricting each layer update to a fixed low-rank form, but this …

parameter-efficient fine-tuning