Aleksandar/NearID-Qwen_1328

--- language: - en license: cc-by-4.0 size_categories: - 10K<n<100K task_categories: - image-feature-extraction pretty_name: NearID-Qwen_1328 (Near-Identity Distractors) dataset_info: features: - name: id dtype: int64 - name: category dtype: string - name: category_description dtype: string - name: nimg1 dtype: image - name: nimg2 dtype: image - name: nimg3 dtype: image - name: n_images dtype: int64 - name: objaverse_id dtype: string - name: prompts1 dtype: string - name: prompts2 dtype: string - name: prompts3 dtype: string - name: quality dtype: string splits: - name: train tags: - nearid - near-identity-distractors - identity-embedding - inpainting - synthetic - metric-learning --- # NearID-Qwen_1328 — Near-Identity Distractors (Qwen-based inpainting) [](https://huggingface.co/Aleksandar/nearid-siglip2) [](https://arxiv.org/abs/2604.01973) [](https://gorluxor.github.io/NearID/) [](https://github.com/Gorluxor/NearID) [](https://www.kaust.edu.sa/) [](https://research.snap.com/) This dataset contains **near-identity distractors** generated by **Qwen-based inpainting** at **1328×1328** resolution as part of the [NearID](https://huggingface.co/Aleksandar/nearid-siglip2) project. Each sample contains up to 3 distractor images (`nimg1`, `nimg2`, `nimg3`): different but visually similar instances inpainted into the **exact same background/context** as the corresponding anchor in the base [Aleksandar/NearID](https://huggingface.co/datasets/Aleksandar/NearID) dataset. These distractors are used to train and evaluate identity embeddings that distinguish true identity from contextual shortcuts. The model and dataset were introduced in the paper [NearID: Identity Representation Learning via Near-identity Distractors](https://huggingface.co/papers/2604.01973). ## Quick Start ```python from datasets import load_dataset # Load this negative source ds = load_dataset("Aleksandar/NearID-Qwen_1328") # Load base positives for anchor/positive pairs positives = load_dataset("Aleksandar/NearID") ``` ## Dataset Structure | Column | Type | Description | |---|---|---| | `id` | int64 | Sample ID (matches the base NearID dataset) | | `category` | string | Object category (`rigid`) | | `category_description` | string | Natural language description of the object | | `nimg1`, `nimg2`, `nimg3` | image | Near-identity distractor images (up to 3 per sample) | | `n_images` | int64 | Number of valid distractor images | | `objaverse_id` | string | Source Objaverse object identifier | | `prompts1`, `prompts2`, `prompts3` | string | Generation prompts for each distractor | | `quality` | string | Quality label | ## How the Distractors Were Generated 1. For each anchor identity in the base NearID dataset, a semantically similar but **different** object instance was retrieved. 2. The distractor instance was inpainted into the **same background** as the anchor using **Qwen-based inpainting**. 3. Resolution: **1328×1328** pixels. This creates a controlled test: a model must rely on intrinsic identity features, not background context, to distinguish anchor from distractor. ## All NearID Datasets | Dataset | Description | Resolution | |---|---|---| | [Aleksandar/NearID](https://huggingface.co/datasets/Aleksandar/NearID) | Multi-view positives (anchor + positive views) | Base | | [Aleksandar/NearID-Flux](https://huggingface.co/datasets/Aleksandar/NearID-Flux) | Near-identity distractors via FLUX.1 inpainting | 512×512 | | [Aleksandar/NearID-Flux_1024](https://huggingface.co/datasets/Aleksandar/NearID-Flux_1024) | Near-identity distractors via FLUX.1 inpainting | 1024×1024 | | [Aleksandar/NearID-FluxC](https://huggingface.co/datasets/Aleksandar/NearID-FluxC) | Near-identity distractors via FLUX.1 Canny-guided inpainting | 512×512 | | [Aleksandar/NearID-FluxC_1024](https://huggingface.co/datasets/Aleksandar/NearID-FluxC_1024) | Near-identity distractors via FLUX.1 Canny-guided inpainting | 1024×1024 | | [Aleksandar/NearID-PowerPaint](https://huggingface.co/datasets/Aleksandar/NearID-PowerPaint) | Near-identity distractors via PowerPaint inpainting | 512×512 | | [Aleksandar/NearID-Qwen](https://huggingface.co/datasets/Aleksandar/NearID-Qwen) | Near-identity distractors via Qwen-based inpainting | 512×512 | | [Aleksandar/NearID-Qwen_1328](https://huggingface.co/datasets/Aleksandar/NearID-Qwen_1328) | Near-identity distractors via Qwen-based inpainting | 1328×1328 | **← this dataset** | [Aleksandar/NearID-SDXL](https://huggingface.co/datasets/Aleksandar/NearID-SDXL) | Near-identity distractors via Stable Diffusion XL inpainting | 512×512 | | [Aleksandar/NearID-SDXL_1024](https://huggingface.co/datasets/Aleksandar/NearID-SDXL_1024) | Near-identity distractors via Stable Diffusion XL inpainting | 1024×1024 | ## Related - **Model:** [Aleksandar/nearid-siglip2](https://huggingface.co/Aleksandar/nearid-siglip2) — NearID identity embedding model - **Paper:** [NearID: Identity Representation Learning via Near-identity Distractors](https://arxiv.org/abs/2604.01973) - **Code:** [github.com/Gorluxor/NearID](https://github.com/Gorluxor/NearID) ## License & Attribution This dataset is released under [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). It is derived from the [SynCD](https://github.com/nupurkmr9/syncd) dataset (MIT License, Copyright 2022 SynCD). If you use this dataset, please cite both NearID and SynCD. ## Citation ```bibtex @article{cvejic2026nearid, title={NearID: Identity Representation Learning via Near-identity Distractors}, author={Cvejic, Aleksandar and Abdal, Rameen and Eldesokey, Abdelrahman and Ghanem, Bernard and Wonka, Peter}, journal={arXiv preprint arXiv:2604.01973}, year={2026} } ```--- 语言: - 英语 许可证: CC BY 4.0 样本量类别: - 10K < n < 100K 任务类别: - 图像特征提取 友好名称: NearID-Qwen_1328（近身份干扰项） 数据集详情: 特征字段: - 名称: id 数据类型: int64 - 名称: category 数据类型: 字符串 - 名称: category_description 数据类型: 字符串 - 名称: nimg1 数据类型: 图像 - 名称: nimg2 数据类型: 图像 - 名称: nimg3 数据类型: 图像 - 名称: n_images 数据类型: int64 - 名称: objaverse_id 数据类型: 字符串 - 名称: prompts1 数据类型: 字符串 - 名称: prompts2 数据类型: 字符串 - 名称: prompts3 数据类型: 字符串 - 名称: quality 数据类型: 字符串 数据划分: - 名称: train 标签: - nearid - 近身份干扰项 - 身份嵌入 - 图像修复 - 合成数据集 - 度量学习 --- # NearID-Qwen_1328 — 近身份干扰项（基于Qwen的图像修复） [](https://huggingface.co/Aleksandar/nearid-siglip2) [](https://arxiv.org/abs/2604.01973) [](https://gorluxor.github.io/NearID/) [](https://github.com/Gorluxor/NearID) [](https://www.kaust.edu.sa/) [](https://research.snap.com/) 本数据集为[NearID](https://huggingface.co/Aleksandar/nearid-siglip2)项目的组成部分，包含由**基于Qwen的图像修复（inpainting）**生成、分辨率为**1328×1328**的**近身份干扰项（near-identity distractors）**。 每个样本最多包含3张干扰图像（`nimg1`、`nimg2`、`nimg3`）：这些图像为与基准数据集[Aleksandar/NearID](https://huggingface.co/datasets/Aleksandar/NearID)中对应锚点图像视觉相似但本质不同的实例，且被修复至与锚点完全一致的背景/上下文环境中。此类干扰项可用于训练和评估能够从上下文捷径中区分真实身份的**身份嵌入（identity embedding）**模型。 本模型与数据集由论文《NearID: Identity Representation Learning via Near-identity Distractors》（[链接](https://huggingface.co/papers/2604.01973)）首次提出。 ## 快速入门 python from datasets import load_dataset # 加载该负样本源数据集 ds = load_dataset("Aleksandar/NearID-Qwen_1328") # 加载基准数据集的正样本以构建锚点-正样本对 positives = load_dataset("Aleksandar/NearID") ## 数据集结构 | 列名 | 数据类型 | 描述 | |---|---|---| | `id` | int64 | 样本ID（与基准NearID数据集一致） | | `category` | 字符串 | 对象类别（本数据集为`rigid`，即刚性物体） | | `category_description` | 字符串 | 对象的自然语言描述 | | `nimg1`、`nimg2`、`nimg3` | 图像 | 近身份干扰图像（每个样本最多3张） | | `n_images` | int64 | 有效干扰图像的数量 | | `objaverse_id` | 字符串 | 来源Objaverse对象标识符 | | `prompts1`、`prompts2`、`prompts3` | 字符串 | 每张干扰图像的生成提示词 | | `quality` | 字符串 | 质量标签 | ## 干扰项生成流程 1. 针对基准NearID数据集中的每个锚点身份，检索一个语义相似但本质不同的对象实例。 2. 使用**基于Qwen的图像修复**模型，将该干扰实例修复至与锚点完全一致的背景环境中。 3. 图像分辨率为**1328×1328**像素。 该构建方式形成了一项可控测试：模型必须依赖内在的身份特征而非背景上下文，才能区分锚点图像与干扰图像。 ## 全部NearID系列数据集 | 数据集 | 描述 | 分辨率 | |---|---|---| | [Aleksandar/NearID](https://huggingface.co/datasets/Aleksandar/NearID) | 多视图正样本（锚点+正样本视图） | 基准分辨率 | | [Aleksandar/NearID-Flux](https://huggingface.co/datasets/Aleksandar/NearID-Flux) | 基于FLUX.1图像修复生成的近身份干扰项 | 512×512 | | [Aleksandar/NearID-Flux_1024](https://huggingface.co/datasets/Aleksandar/NearID-Flux_1024) | 基于FLUX.1图像修复生成的近身份干扰项 | 1024×1024 | | [Aleksandar/NearID-FluxC](https://huggingface.co/datasets/Aleksandar/NearID-FluxC) | 基于FLUX.1 Canny引导式图像修复生成的近身份干扰项 | 512×512 | | [Aleksandar/NearID-FluxC_1024](https://huggingface.co/datasets/Aleksandar/NearID-FluxC_1024) | 基于FLUX.1 Canny引导式图像修复生成的近身份干扰项 | 1024×1024 | | [Aleksandar/NearID-PowerPaint](https://huggingface.co/datasets/Aleksandar/NearID-PowerPaint) | 基于PowerPaint图像修复生成的近身份干扰项 | 512×512 | | [Aleksandar/NearID-Qwen](https://huggingface.co/datasets/Aleksandar/NearID-Qwen) | 基于Qwen的图像修复生成的近身份干扰项 | 512×512 | | [Aleksandar/NearID-Qwen_1328](https://huggingface.co/datasets/Aleksandar/NearID-Qwen_1328) | 基于Qwen的图像修复生成的近身份干扰项 | 1328×1328 | **← 本数据集** | [Aleksandar/NearID-SDXL](https://huggingface.co/datasets/Aleksandar/NearID-SDXL) | 基于Stable Diffusion XL图像修复生成的近身份干扰项 | 512×512 | | [Aleksandar/NearID-SDXL_1024](https://huggingface.co/datasets/Aleksandar/NearID-SDXL_1024) | 基于Stable Diffusion XL图像修复生成的近身份干扰项 | 1024×1024 | ## 相关资源 - **模型**：[Aleksandar/nearid-siglip2](https://huggingface.co/Aleksandar/nearid-siglip2) — NearID身份嵌入模型 - **论文**：[NearID: Identity Representation Learning via Near-identity Distractors](https://arxiv.org/abs/2604.01973) - **代码**：[github.com/Gorluxor/NearID](https://github.com/Gorluxor/NearID) ## 许可证与署名 本数据集采用[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)协议发布，其衍生自[SynCD](https://github.com/nupurkmr9/syncd)数据集（采用MIT许可证，版权归2022 SynCD所有）。若使用本数据集，请同时引用NearID与SynCD相关文献。 ## 引用格式 bibtex @article{cvejic2026nearid, title={NearID: Identity Representation Learning via Near-identity Distractors}, author={Cvejic, Aleksandar and Abdal, Rameen and Eldesokey, Abdelrahman and Ghanem, Bernard and Wonka, Peter}, journal={arXiv preprint arXiv:2604.01973}, year={2026} }