NearID：基于近身份干扰因子的身份表征学习

摘要

在评估个性化生成与图像编辑等以身份识别为核心的任务时，现有视觉编码器往往将目标身份与背景信息相纠缠，导致表征和度量结果不可靠。我们首次提出基于近身份干扰样本（NearID）的 principled 框架来解决这一缺陷：通过将语义相似但身份不同的实例置于与参考图像完全一致的背景中，消除上下文捷径干扰，使身份特征成为唯一的判别信号。基于此原理，我们构建了包含1.9万个身份、31.6万组背景匹配干扰样本的NearID数据集，并制定了严格的边界评估协议。在该设定下，预训练编码器表现不佳，其样本成功率（SSR，一种严格的边界身份判别指标）低至30.7%，且常将干扰样本排序置于真实跨视角匹配结果之上。针对此问题，我们在冻结骨干网络的基础上通过双层对比目标学习身份感知表征，强制建立“同一身份 > 近身份干扰样本 > 随机负样本”的层级关系。该方法将SSR提升至99.2%，局部判别能力增强28.0%，并在人类对齐的个性化评估基准DreamBench++上展现出更优的人类判断一致性。项目页面：https://gorluxor.github.io/NearID/

English

When evaluating identity-focused tasks such as personalized generation and image editing, existing vision encoders entangle object identity with background context, leading to unreliable representations and metrics. We introduce the first principled framework to address this vulnerability using Near-identity (NearID) distractors, where semantically similar but distinct instances are placed on the exact same background as a reference image, eliminating contextual shortcuts and isolating identity as the sole discriminative signal. Based on this principle, we present the NearID dataset (19K identities, 316K matched-context distractors) together with a strict margin-based evaluation protocol. Under this setting, pre-trained encoders perform poorly, achieving Sample Success Rates (SSR), a strict margin-based identity discrimination metric, as low as 30.7% and often ranking distractors above true cross-view matches. We address this by learning identity-aware representations on a frozen backbone using a two-tier contrastive objective enforcing the hierarchy: same identity > NearID distractor > random negative. This improves SSR to 99.2%, enhances part-level discrimination by 28.0%, and yields stronger alignment with human judgments on DreamBench++, a human-aligned benchmark for personalization. Project page: https://gorluxor.github.io/NearID/

NearID：基于近身份干扰因子的身份表征学习

NearID: Identity Representation Learning via Near-identity Distractors

摘要

Support