Salvato in:
Dettagli Bibliografici
Autori principali: Chae, Julia, Kolkin, Nicholas, Wang, Jui-Hsien, Zhang, Richard, Beery, Sara, Ham, Cusuh
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.05039
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915919036416000
author Chae, Julia
Kolkin, Nicholas
Wang, Jui-Hsien
Zhang, Richard
Beery, Sara
Ham, Cusuh
author_facet Chae, Julia
Kolkin, Nicholas
Wang, Jui-Hsien
Zhang, Richard
Beery, Sara
Ham, Cusuh
contents Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to match this capability, and progress toward identity-focused tasks such as personalized image generation is slowed by a lack of identity-focused evaluation metrics. To help facilitate progress, we propose ID-Sim, a feed-forward metric designed to faithfully reflect human selective sensitivity. To build ID-Sim, we curate a high-quality training set of images spanning diverse real-world domains, augmented with generative synthetic data that provides controlled, fine-grained identity and contextual variations. We evaluate our metric on a new unified evaluation benchmark for assessing consistency with human annotations across identity-focused recognition, retrieval, and generative tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05039
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ID-Sim: An Identity-Focused Similarity Metric
Chae, Julia
Kolkin, Nicholas
Wang, Jui-Hsien
Zhang, Richard
Beery, Sara
Ham, Cusuh
Computer Vision and Pattern Recognition
Artificial Intelligence
Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to match this capability, and progress toward identity-focused tasks such as personalized image generation is slowed by a lack of identity-focused evaluation metrics. To help facilitate progress, we propose ID-Sim, a feed-forward metric designed to faithfully reflect human selective sensitivity. To build ID-Sim, we curate a high-quality training set of images spanning diverse real-world domains, augmented with generative synthetic data that provides controlled, fine-grained identity and contextual variations. We evaluate our metric on a new unified evaluation benchmark for assessing consistency with human annotations across identity-focused recognition, retrieval, and generative tasks.
title ID-Sim: An Identity-Focused Similarity Metric
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.05039