Id-sim: An Identity-focused Similarity Metric

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychae2026id

Related papers

• Dreamsim: Learning New Dimensions Of Human Visual Similarity Using Synthetic Data (2023)5.84
• A Similarity Inference Metric For Rgb-infrared Cross-modality Person Re-identification (2020)12.99
• CSIM: A Copula-based Similarity Index Sensitive To Local Changes For Image Quality Assessment (2024)2.16
• Introspective Deep Metric Learning For Image Retrieval (2022)3.50
• Introspective Deep Metric Learning (2023)13.85
• Finer-personalization Rank: Fine-grained Retrieval Examines Identity Preservation For Personalized Generation (2025)0.00
• Genecis: A Benchmark For General Conditional Image Similarity (2023)10.07
• Lipsim: A Provably Robust Perceptual Similarity Metric (2023)2.76