Saved in:
Bibliographic Details
Main Authors: Kilrain, Connor, Carlyn, David, Chae, Julia, Beery, Sara, Chao, Wei-Lun, Gu, Jianyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.19026
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914213953273856
author Kilrain, Connor
Carlyn, David
Chae, Julia
Beery, Sara
Chao, Wei-Lun
Gu, Jianyang
author_facet Kilrain, Connor
Carlyn, David
Chae, Julia
Beery, Sara
Chao, Wei-Lun
Gu, Jianyang
contents The rise of personalized generative models raises a central question: how should we evaluate identity preservation? Given a reference image (e.g., one's pet), we expect the generated image to retain precise details attached to the subject's identity. However, current generative evaluation metrics emphasize the overall semantic similarity between the reference and the output, and overlook these fine-grained discriminative details. We introduce Finer-Personalization Rank, an evaluation protocol tailored to identity preservation. Instead of pairwise similarity, Finer-Personalization Rank adopts a ranking view: it treats each generated image as a query against an identity-labeled gallery consisting of visually similar real images. Retrieval metrics (e.g., mean average precision) measure performance, where higher scores indicate that identity-specific details (e.g., a distinctive head spot) are preserved. We assess identity at multiple granularities -- from fine-grained categories (e.g., bird species, car models) to individual instances (e.g., re-identification). Across CUB, Stanford Cars, and animal Re-ID benchmarks, Finer-Personalization Rank more faithfully reflects identity retention than semantic-only metrics and reveals substantial identity drift in several popular personalization methods. These results position the gallery-based protocol as a principled and practical evaluation for personalized generation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19026
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation
Kilrain, Connor
Carlyn, David
Chae, Julia
Beery, Sara
Chao, Wei-Lun
Gu, Jianyang
Computer Vision and Pattern Recognition
Artificial Intelligence
The rise of personalized generative models raises a central question: how should we evaluate identity preservation? Given a reference image (e.g., one's pet), we expect the generated image to retain precise details attached to the subject's identity. However, current generative evaluation metrics emphasize the overall semantic similarity between the reference and the output, and overlook these fine-grained discriminative details. We introduce Finer-Personalization Rank, an evaluation protocol tailored to identity preservation. Instead of pairwise similarity, Finer-Personalization Rank adopts a ranking view: it treats each generated image as a query against an identity-labeled gallery consisting of visually similar real images. Retrieval metrics (e.g., mean average precision) measure performance, where higher scores indicate that identity-specific details (e.g., a distinctive head spot) are preserved. We assess identity at multiple granularities -- from fine-grained categories (e.g., bird species, car models) to individual instances (e.g., re-identification). Across CUB, Stanford Cars, and animal Re-ID benchmarks, Finer-Personalization Rank more faithfully reflects identity retention than semantic-only metrics and reveals substantial identity drift in several popular personalization methods. These results position the gallery-based protocol as a principled and practical evaluation for personalized generation.
title Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.19026