用近似身份干扰项测试并提升图像身份表征的可靠性
NearID: Identity Representation Learning via Near-identity Distractors
- 设计近似身份干扰样本，隔离身份与背景的混淆
- 预训练模型在严格评测下身份识别率仅30.7%，远低于真实匹配
- 新方法使识别率提升至99.2%，更符合人类判断
在个性化生成与图像编辑等身份相关任务中，现有视觉编码器常将对象身份与背景上下文混杂，导致表征不可靠。本文提出首个基于近身份干扰项（NearID）的系统性框架，通过将语义相似但不同的实例置于与参考图完全相同的背景下，消除上下文捷径，使身份成为唯一判别信号。基于此，构建了包含19,000个身份、316,000个匹配上下文干扰项的NearID数据集，并采用严格的边距评估协议。在此设置下，预训练编码器表现不佳，样本成功率达30.7%，且常将干扰项排在真实跨视角匹配之上。为此，我们在冻结主干网络上引入双层对比学习目标，强制建立‘同身份 > NearID干扰项 > 随机负样本’的层次关系。该方法使样本成功率提升至99.2%，部分级辨别能力提高28.0%，并在DreamBench++（一个面向个性化的对齐人类判断的基准）上展现出更强的人类一致性。
原文摘要 · Abstract (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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。