Re-identification
-
Image-Text Knowledge Modeling for Unsupervised Multi-Scenario Person Re-Identification
2026-01-16 12:45:01Zhiqi Pang, Lingling Zhao, Yang Liu, Chunyu Wang, Gaurav SharmaAbstract
We propose unsupervised multi-scenario (UMS) person re-identification (ReID) as a new task that expands ReID across diverse scenarios (cross-resolution, clothing change, etc.) within a single coherent framework. To tackle UMS-ReID, we introduce image-text knowledge modeling (ITKM) -- a three-stage framework that effectively exploits the representational power of vision-language models. We start with a pre-trained CLIP model with an image encoder and a text encoder. In Stage I, we introduce a scenario embedding in the image encoder and fine-tune the encoder to adaptively leverage knowledge from multiple scenarios. In Stage II, we optimize a set of learned text embeddings to associate with pseudo-labels from Stage I and introduce a multi-scenario separation loss to increase the divergence between inter-scenario text representations. In Stage III, we first introduce cluster-level and instance-level heterogeneous matching modules to obtain reliable heterogeneous positive pairs (e.g., a visible image and an infrared image of the same person) within each scenario. Next, we propose a dynamic text representation update strategy to maintain consistency between text and image supervision signals. Experimental results across multiple scenarios demonstrate the superiority and generalizability of ITKM; it not only outperforms existing scenario-specific methods but also enhances overall performance by integrating knowledge from multiple scenarios.
Abstract (translated)
我们提出了一种新的任务——无监督多场景（UMS）人员重新识别（ReID），该任务旨在通过单一连贯框架扩展ReID在各种场景中的应用，如跨分辨率和着装变化等。为了解决UMS-ReID问题，我们引入了图像文本知识建模（ITKM）——一个三阶段框架，有效地利用了视觉-语言模型的表征能力。 首先，从预训练的CLIP模型开始，该模型包含一个图像编码器和一个文本编码器。在第一阶段，我们在图像编码器中引入场景嵌入，并微调编码器以适应性地利用来自多个场景的知识。第二阶段，我们优化了一组学习到的文本嵌入与第一阶段生成的伪标签相关联，并提出了一个多场景分离损失函数，以便增加跨场景文本表示之间的差异。 在第三阶段，首先引入了群级别和实例级别的异构匹配模块，在每个场景中获取可靠的异构正样本对（例如，同一人的可见图像和红外图像）。接下来，我们提出了一种动态文本表征更新策略，以保持文本和图像监督信号之间的一致性。跨多个场景的实验结果表明，ITKM具有优越性和泛化能力；它不仅超越了现有的特定场景方法，并且通过整合来自多场景的知识提升了整体性能。
URL
https://arxiv.org/abs/2601.11243
PDF
-
Disentangled Concept Representation for Text-to-image Person Re-identification
2026-01-15 04:08:53Giyeol Kim, Chanho EomAbstract
Text-to-image person re-identification (TIReID) aims to retrieve person images from a large gallery given free-form textual descriptions. TIReID is challenging due to the substantial modality gap between visual appearances and textual expressions, as well as the need to model fine-grained correspondences that distinguish individuals with similar attributes such as clothing color, texture, or outfit style. To address these issues, we propose DiCo (Disentangled Concept Representation), a novel framework that achieves hierarchical and disentangled cross-modal alignment. DiCo introduces a shared slot-based representation, where each slot acts as a part-level anchor across modalities and is further decomposed into multiple concept blocks. This design enables the disentanglement of complementary attributes (\textit{e.g.}, color, texture, shape) while maintaining consistent part-level correspondence between image and text. Extensive experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate that our framework achieves competitive performance with state-of-the-art methods, while also enhancing interpretability through explicit slot- and block-level representations for more fine-grained retrieval results.
Abstract (translated)
文本到图像的人再识别（TIReID）的目标是从大型图片库中检索出给定自由格式的文字描述所对应的人体图像。由于视觉外观与文字表达之间存在显著的模态差距，以及需要建模精细粒度的对应关系以区分具有类似属性（如服装颜色、纹理或着装风格）的个体，TIReID变得极具挑战性。为了应对这些问题，我们提出了一种新的框架DiCo（分离概念表示），该框架实现了层次化和独立的跨模式对齐。 DiCo引入了基于共享槽位的表示方法，在这种方法中，每个槽作为一个跨模态的部分级锚点，并进一步分解成多个概念块。这种设计使得可以将互补属性（如颜色、纹理、形状）分离出来，同时在图像与文本之间保持一致的部分级对应关系。广泛的实验表明，我们的框架在CUHK-PEDES、ICFG-PEDES和RSTPReid数据集上实现了具有竞争力的性能，并通过显式的槽位及块级别表示提升了模型的可解释性，从而能够提供更精细粒度的检索结果。
URL
https://arxiv.org/abs/2601.10053
PDF
-
Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server
2026-01-14 14:55:14Yue Yao, Ruining Yang, Tom GedeonAbstract
We explore a situation in which the target domain is accessible, but real-time data annotation is not feasible. Instead, we would like to construct an alternative training set from a large-scale data server so that a competitive model can be obtained. For this problem, because the target domain usually exhibits distinct modes (i.e., semantic clusters representing data distribution), if the training set does not contain these target modes, the model performance would be compromised. While prior existing works improve algorithms iteratively, our research explores the often-overlooked potential of optimizing the structure of the data server. Inspired by the hierarchical nature of web search engines, we introduce a hierarchical data server, together with a bipartite mode matching algorithm (BMM) to align source and target modes. For each target mode, we look in the server data tree for the best mode match, which might be large or small in size. Through bipartite matching, we aim for all target modes to be optimally matched with source modes in a one-on-one fashion. Compared with existing training set search algorithms, we show that the matched server modes constitute training sets that have consistently smaller domain gaps with the target domain across object re-identification (re-ID) and detection tasks. Consequently, models trained on our searched training sets have higher accuracy than those trained otherwise. BMM allows data-centric unsupervised domain adaptation (UDA) orthogonal to existing model-centric UDA methods. By combining the BMM with existing UDA methods like pseudo-labeling, further improvement is observed.
Abstract (translated)
我们探讨了一种情况，即目标领域可以访问，但实时数据标注不可行。为此，我们希望从大规模的数据服务器中构建一个替代的训练集，从而获得具有竞争力的模型。对于这个问题，因为目标域通常表现出不同的模式（即代表数据分布的语义簇），如果训练集中不包含这些目标模式，那么模型性能将受到影响。 以往的研究工作通过迭代改进算法来解决这一问题，而我们的研究则探索了往往被忽视的数据服务器结构优化潜力。受网络搜索引擎层次结构的启发，我们引入了一个分层数据服务器，并结合双轨模式匹配算法（BMM）以对齐源域和目标域的模式。对于每个目标模式，在服务器数据树中寻找最佳模式匹配，无论其大小如何。通过双轨匹配，我们的目的是让所有目标模式都能与源模式一对一地实现最优匹配。 相较于现有的训练集搜索算法，我们展示了所匹配的服务器模式构成的训练集在跨对象重识别（re-ID）和检测任务中的域差距始终较小。因此，在使用我们搜索到的训练集进行训练后，模型具有更高的准确性。 BMM使数据为中心的无监督领域适应（UDA）方法与现有以模型为中心的UDA方法相辅相成。通过结合BMM和其他现有的UDA方法（如伪标签），进一步改进了性能。
URL
https://arxiv.org/abs/2601.09531
PDF
-
StegoStylo: Squelching Stylometric Scrutiny through Steganographic Stitching
2026-01-14 00:49:20Robert DilworthAbstract
Stylometry--the identification of an author through analysis of a text's style (i.e., authorship attribution)--serves many constructive purposes: it supports copyright and plagiarism investigations, aids detection of harmful content, offers exploratory cues for certain medical conditions (e.g., early signs of dementia or depression), provides historical context for literary works, and helps uncover misinformation and disinformation. In contrast, when stylometry is employed as a tool for authorship verification--confirming whether a text truly originates from a claimed author--it can also be weaponized for malicious purposes. Techniques such as de-anonymization, re-identification, tracking, profiling, and downstream effects like censorship illustrate the privacy threats that stylometric analysis can enable. Building on these concerns, this paper further explores how adversarial stylometry combined with steganography can counteract stylometric analysis. We first present enhancements to our adversarial attack, $\textit{TraceTarnish}$, providing stronger evidence of its capacity to confound stylometric systems and reduce their attribution and verification accuracy. Next, we examine how steganographic embedding can be fine-tuned to mask an author's stylistic fingerprint, quantifying the level of authorship obfuscation achievable as a function of the proportion of words altered with zero-width Unicode characters. Based on our findings, steganographic coverage of 33% or higher seemingly ensures authorship obfuscation. Finally, we reflect on the ways stylometry can be used to undermine privacy and argue for the necessity of defensive tools like $\textit{TraceTarnish}$.
Abstract (translated)
语体测量法——通过分析文本的风格来识别作者（即，确定作者身份）——在许多建设性方面发挥着重要作用：它支持版权和抄袭调查，有助于检测有害内容，为某些医疗状况提供探索线索（例如痴呆症或抑郁症的早期迹象），为文学作品提供历史背景，并帮助揭露错误信息和虚假信息。然而，当语体测量被用作作者身份验证工具——确认文本是否真正来自声称的作者时——它也可能被用于恶意目的。诸如去匿名化、重新识别、跟踪、个人画像以及由此产生的审查等隐私威胁都可能因语体分析而引发。 基于这些担忧，本文进一步探讨了通过结合对抗性语体测量和隐写术来对抗语体分析的方法。首先，我们介绍了对我们的对抗攻击技术$\textit{TraceTarnish}$的改进，提供了更强有力的证据证明其能够混淆语体系统的识别能力，并降低其归因与验证的准确性。接下来，我们将研究如何通过调整隐写术嵌入以掩盖作者的独特风格特征，量化使用零宽度Unicode字符修改的比例对作者身份模糊化程度的影响。根据我们的研究成果，在33%或更高的隐写覆盖范围内，似乎能够确保有效的作者身份混淆。 最后，我们反思了语体测量如何被用于侵犯隐私，并主张需要防御性工具如$\textit{TraceTarnish}$来保护个人免受此类技术带来的风险。
URL
https://arxiv.org/abs/2601.09056
PDF
-
S3-CLIP: Video Super Resolution for Person-ReID
2026-01-13 18:46:37Tamas Endrei, Gyorgy CsereyAbstract
Tracklet quality is often treated as an afterthought in most person re-identification (ReID) methods, with the majority of research presenting architectural modifications to foundational models. Such approaches neglect an important limitation, posing challenges when deploying ReID systems in real-world, difficult scenarios. In this paper, we introduce S3-CLIP, a video super-resolution-based CLIP-ReID framework developed for the VReID-XFD challenge at WACV 2026. The proposed method integrates recent advances in super-resolution networks with task-driven super-resolution pipelines, adapting them to the video-based person re-identification setting. To the best of our knowledge, this work represents the first systematic investigation of video super-resolution as a means of enhancing tracklet quality for person ReID, particularly under challenging cross-view conditions. Experimental results demonstrate performance competitive with the baseline, achieving 37.52% mAP in aerial-to-ground and 29.16% mAP in ground-to-aerial scenarios. In the ground-to-aerial setting, S3-CLIP achieves substantial gains in ranking accuracy, improving Rank-1, Rank-5, and Rank-10 performance by 11.24%, 13.48%, and 17.98%, respectively.
Abstract (translated)
在大多数人物重新识别（ReID）方法中，轨迹质量通常被当作次要问题处理，而多数研究集中在对基础模型进行架构上的改进。这种做法忽视了一个重要的局限性，在实际部署ReID系统时会遇到挑战，尤其是在复杂且困难的场景下。在这篇论文中，我们介绍了S3-CLIP框架，这是一个基于视频超分辨率（Video Super-Resolution）和CLIP-ReID技术相结合的方法，并用于WACV 2026年举办的VReID-XFD竞赛。该方法将最近在超分辨率网络中的进展与任务驱动的超分辨率流程集成起来，适应于基于视频的人物重新识别场景。 据我们所知，这项工作是首次系统性地研究视频超分辨率技术如何提升轨迹质量以增强人物ReID性能的研究，特别是在跨视角（cross-view）条件下。实验结果表明，我们的方法在性能上与基准线相当，并且在从空中到地面和从地面到空中的场景中分别达到了37.52%的mAP和29.16%的mAP。尤其是在地面到空中设置的情况下，S3-CLIP框架显著提高了排名准确度，在Rank-1、Rank-5和Rank-10性能方面分别提升了11.24%，13.48%，以及17.98%。
URL
https://arxiv.org/abs/2601.08807
PDF
-
Near-perfect photo-ID of the Hula painted frog with zero-shot deep local-feature matching
2026-01-13 18:32:43Maayan Yesharim, R. G. Bina Perl, Uri Roll, Sarig Gafny, Eli Geffen, Yoav RamAbstract
Accurate individual identification is essential for monitoring rare amphibians, yet invasive marking is often unsuitable for critically endangered species. We evaluate state-of-the-art computer-vision methods for photographic re-identification of the Hula painted frog (Latonia nigriventer) using 1,233 ventral images from 191 individuals collected during 2013-2020 capture-recapture surveys. We compare deep local-feature matching in a zero-shot setting with deep global-feature embedding models. The local-feature pipeline achieves 98% top-1 closed-set identification accuracy, outperforming all global-feature models; fine-tuning improves the best global-feature model to 60% top-1 (91% top-10) but remains below local matching. To combine scalability with accuracy, we implement a two-stage workflow in which a fine-tuned global-feature model retrieves a short candidate list that is re-ranked by local-feature matching, reducing end-to-end runtime from 6.5-7.8 hours to ~38 minutes while maintaining ~96% top-1 closed-set accuracy on the labeled dataset. Separation of match scores between same- and different-individual pairs supports thresholding for open-set identification, enabling practical handling of novel individuals. We deploy this pipeline as a web application for routine field use, providing rapid, standardized, non-invasive identification to support conservation monitoring and capture-recapture analyses. Overall, in this species, zero-shot deep local-feature matching outperformed global-feature embedding and provides a strong default for photo-identification.
Abstract (translated)
准确的个体识别对于监测稀有两栖动物至关重要，然而，侵入性标记方法通常不适用于极度濒危物种。我们评估了最先进的计算机视觉方法，用于2013年至2020年间在捕捉和再捕捉调查中收集到的191只霍拉彩蛙（Latonia nigriventer）的1,233张腹部图像的摄影重新识别。我们在零样本设置下比较了深度局部特征匹配与深度全局特征嵌入模型的效果。局部特征管道达到了98%的第一名封闭集识别准确率，优于所有全局特征模型；微调将最佳全局特征模型改进至60%的第一名（91%的前十名），但仍低于局部匹配的表现。为了结合可扩展性和准确性，我们实施了一个两阶段工作流程，在该流程中，一个微调后的全局特征模型检索出一个简短的候选名单，然后通过局部特征匹配重新排序，将端到端运行时间从6.5至7.8小时减少到了大约38分钟，同时保持了标记数据集上的约96%的第一名封闭集准确率。同源个体与不同个体配对之间的匹配得分差异支持阈值设置以进行开放集识别，从而能够处理新出现的个体。我们将此流程部署为网络应用程序供日常现场使用，提供快速、标准化且非侵入性的识别方式来支持保护监测和捕捉再释放分析。总体而言，在该物种中，零样本深度局部特征匹配优于全局特征嵌入，并提供了照片识别的一个强大的默认选项。
URL
https://arxiv.org/abs/2601.08798
PDF
-
Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset
Abstract
On December 4, 2025, Anthropic released Anthropic Interviewer, an AI tool for running qualitative interviews at scale, along with a public dataset of 1,250 interviews with professionals, including 125 scientists, about their use of AI for research. Focusing on the scientist subset, I show that widely available LLMs with web search and agentic capabilities can link six out of twenty-four interviews to specific scientific works, recovering associated authors and, in some cases, uniquely identifying the interviewees. My contribution is to show that modern LLM-based agents make such re-identification attacks easy and low-effort: off-the-shelf tools can, with a few natural-language prompts, search the web, cross-reference details, and propose likely matches, effectively lowering the technical barrier. Existing safeguards can be bypassed by breaking down the re-identification into benign tasks. I outline the attack at a high level, discuss implications for releasing rich qualitative data in the age of LLM agents, and propose mitigation recommendations and open problems. I have notified Anthropic of my findings.
Abstract (translated)
2025年12月4日，Anthropic发布了名为“Anthropic Interviewer”的AI工具，该工具可以大规模地运行定性访谈，并同时发布了一个包含1250份专业人士访谈的公共数据集（包括125名科学家），讨论他们使用AI进行研究的情况。特别关注于科学家这一子群体，我展示了市面上广泛可用的大规模语言模型（LLMs）结合网络搜索和代理功能可以将六分之一的二十四位受访者的访谈链接到具体科学作品上，并能够恢复关联作者，在某些情况下甚至能够唯一识别出受访者本人。 我的贡献在于展示现代基于LLM的代理使这种重新识别攻击变得简单且低投入：现成工具可以通过几个自然语言提示在网络上搜索、相互参考细节并提出可能匹配项，从而有效降低技术门槛。现有的安全措施可以被打破，通过将重新识别分解为看似无害的任务而绕过。 我概述了该攻击的高级别策略，并讨论在LLM代理时代发布丰富定性数据的影响，提出了缓解建议和开放问题。我已经通知了Anthropic我的发现。
URL
https://arxiv.org/abs/2601.05918
PDF
-
SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances
2026-01-09 05:22:58Qiwei Yang, Pingping Zhang, Yuhao Wang, Zijing GongAbstract
Video-based Person Re-IDentification (VPReID) aims to retrieve the same person from videos captured by non-overlapping cameras. At extreme far distances, VPReID is highly challenging due to severe resolution degradation, drastic viewpoint variation and inevitable appearance noise. To address these issues, we propose a Scale-Adaptive framework with Shape Priors for VPReID, named SAS-VPReID. The framework is built upon three complementary modules. First, we deploy a Memory-Enhanced Visual Backbone (MEVB) to extract discriminative feature representations, which leverages the CLIP vision encoder and multi-proxy memory. Second, we propose a Multi-Granularity Temporal Modeling (MGTM) to construct sequences at multiple temporal granularities and adaptively emphasize motion cues across scales. Third, we incorporate Prior-Regularized Shape Dynamics (PRSD) to capture body structure dynamics. With these modules, our framework can obtain more discriminative feature representations. Experiments on the VReID-XFD benchmark demonstrate the effectiveness of each module and our final framework ranks the first on the VReID-XFD challenge leaderboard. The source code is available at this https URL.
Abstract (translated)
基于视频的人再识别（VPReID）的目标是从不同摄像头捕获的视频中检索同一个人。在极端远距离情况下，由于分辨率严重退化、视角变化剧烈以及不可避免的外观噪声，VPReID变得非常具有挑战性。为解决这些问题，我们提出了一种名为SAS-VPReID的尺度自适应框架，并引入形状先验。该框架基于三个互补模块构建： 1. 我们部署了一个增强型视觉骨干网（Memory-Enhanced Visual Backbone, MEVB），用于提取判别性的特征表示，它利用了CLIP视觉编码器和多代理记忆。 2. 提出了一个多粒度时间建模（Multi-Granularity Temporal Modeling, MGTM）模块，以在多个时间粒度上构建序列，并适应性地强调不同尺度上的运动线索。 3. 我们融入了一种先验正则化的形状动态模型（Prior-Regularized Shape Dynamics, PRSD），用于捕捉人体结构的变化。 通过这些模块的结合，我们的框架可以获得更具判别性的特征表示。在VReID-XFD基准测试上进行的实验展示了每个模块的有效性，并且我们最终的框架在VReID-XFD挑战排行榜中排名第一。源代码可在上述链接获取。
URL
https://arxiv.org/abs/2601.05535
PDF
-
DCG ReID: Disentangling Collaboration and Guidance Fusion Representations for Multi-modal Vehicle Re-Identification
2026-01-06 11:09:19Aihua Zheng, Ya Gao, Shihao Li, Chenglong Li, Jin TangAbstract
Multi-modal vehicle Re-Identification (ReID) aims to leverage complementary information from RGB, Near Infrared (NIR), and Thermal Infrared (TIR) modalities to retrieve the same vehicle. The challenges of multi-modal vehicle ReID arise from the uncertainty of modality quality distribution induced by inherent discrepancies across modalities, resulting in distinct conflicting fusion requirements for data with balanced and unbalanced quality distributions. Existing methods handle all multi-modal data within a single fusion model, overlooking the different needs of the two data types and making it difficult to decouple the conflict between intra-class consistency and inter-modal heterogeneity. To this end, we propose Disentangle Collaboration and Guidance Fusion Representations for Multi-modal Vehicle ReID (DCG-ReID). Specifically, to disentangle heterogeneous quality-distributed modal data without mutual interference, we first design the Dynamic Confidence-based Disentangling Weighting (DCDW) mechanism: dynamically reweighting three-modal contributions via interaction-derived modal confidence to build a disentangled fusion framework. Building on DCDW, we develop two scenario-specific fusion strategies: (1) for balanced quality distributions, Collaboration Fusion Module (CFM) mines pairwise consensus features to capture shared discriminative information and boost intra-class consistency; (2) for unbalanced distributions, Guidance Fusion Module (GFM) implements differential amplification of modal discriminative disparities to reinforce dominant modality advantages, guide auxiliary modalities to mine complementary discriminative info, and mitigate inter-modal divergence to boost multi-modal joint decision performance. Extensive experiments on three multi-modal ReID benchmarks (WMVeID863, MSVR310, RGBNT100) validate the effectiveness of our method. Code will be released upon acceptance.
Abstract (translated)
多模态车辆再识别（ReID）旨在利用RGB、近红外（NIR）和热红外（TIR）等不同模式提供的互补信息，来检索同一辆车。这一任务的挑战在于，由于各模式之间的固有差异性导致了它们质量分布的不确定性，从而产生了对平衡和不平衡质量数据融合的不同要求。现有的方法通常采用单一的融合模型处理所有多模态数据，忽视了两种类型数据的具体需求，并且难以分离类内一致性与跨模态异质性的矛盾。 为了解决这些问题，我们提出了“分解协作和指导性融合表示用于多模态车辆ReID”（DCG-ReID）。具体来说，为了在不互相干扰的情况下将不同质量分布的异构模式数据解耦，我们首先设计了基于动态置信度的分离加权机制（DCDW）：通过由交互得出的模式自信度来动态地重新调整三模态贡献权重，并构建一个解耦的融合框架。在此基础上，针对两种不同的场景分别开发出两个特定的融合策略： 1. 对于平衡质量分布的情况，协作融合模块（CFM）挖掘成对共识特征以捕捉共享区分信息并增强类内一致性。 2. 对于不平衡分布情况，则采用指导性融合模块（GFM），通过差异化放大模式间的区分差异来加强主导模态的优势，并引导辅助模态去挖掘补充的区分信息，从而缓解跨模态分歧，提升多模态联合决策性能。 我们已经在三个多模态ReID基准测试集（WMVeID863、MSVR310和RGBNT100）上进行了广泛的实验验证了该方法的有效性。在论文被接受后将公开代码。
URL
https://arxiv.org/abs/2601.02924
PDF
-
Mask-Guided Multi-Task Network for Face Attribute Recognition
2026-01-04 07:21:15Gong Gao, Zekai Wang, Jian Zhao, Ziqi Xie, Xianhui Liu, Weidong ZhaoAbstract
Face Attribute Recognition (FAR) plays a crucial role in applications such as person re-identification, face retrieval, and face editing. Conventional multi-task attribute recognition methods often process the entire feature map for feature extraction and attribute classification, which can produce redundant features due to reliance on global regions. To address these challenges, we propose a novel approach emphasizing the selection of specific feature regions for efficient feature learning. We introduce the Mask-Guided Multi-Task Network (MGMTN), which integrates Adaptive Mask Learning (AML) and Group-Global Feature Fusion (G2FF) to address the aforementioned limitations. Leveraging a pre-trained keypoint annotation model and a fully convolutional network, AML accurately localizes critical facial parts (e.g., eye and mouth groups) and generates group masks that delineate meaningful feature regions, thereby mitigating negative transfer from global region usage. Furthermore, G2FF combines group and global features to enhance FAR learning, enabling more precise attribute identification. Extensive experiments on two challenging facial attribute recognition datasets demonstrate the effectiveness of MGMTN in improving FAR performance.
Abstract (translated)
面部属性识别（FAR）在人员再识别、人脸检索和人脸编辑等应用中扮演着重要角色。传统的多任务属性识别方法通常在整个特征图上进行特征提取和属性分类，这可能会由于依赖全局区域而导致冗余特征的产生。为了解决这些问题，我们提出了一种新的方法，强调选择特定的特征区域以实现高效的特征学习。为此，我们引入了Mask-Guided Multi-Task Network（MGMTN），该网络结合了自适应掩码学习（Adaptive Mask Learning, AML）和组全局特征融合（Group-Global Feature Fusion, G2FF），旨在解决上述限制。 AML利用预训练的关键点标注模型和全卷积网络，能够精确定位关键面部部分（如眼睛和嘴巴等区域），并生成分组掩码以界定有意义的特征区域，从而减轻使用全局区域所带来的负面转移效应。此外，G2FF结合了组内和全局特征，增强FAR的学习能力，使得属性识别更加精确。 在两个具有挑战性的面部属性识别数据集上的广泛实验表明，MGMTN能够有效提升FAR性能。
URL
https://arxiv.org/abs/2601.01408
PDF
-
Advanced Machine Learning Approaches for Enhancing Person Re-Identification Performance
2026-01-04 03:55:59Dang H. Pham, Tu N. Nguyen, Hoa N. NguyenAbstract
Person re-identification (ReID) plays a critical role in intelligent surveillance systems by linking identities across multiple cameras in complex environments. However, ReID faces significant challenges such as appearance variations, domain shifts, and limited labeled data. This dissertation proposes three advanced approaches to enhance ReID performance under supervised, unsupervised domain adaptation (UDA), and fully unsupervised settings. First, SCM-ReID integrates supervised contrastive learning with hybrid loss optimization (classification, center, triplet, and centroid-triplet losses), improving discriminative feature representation and achieving state-of-the-art accuracy on Market-1501 and CUHK03 datasets. Second, for UDA, IQAGA and DAPRH combine GAN-based image augmentation, domain-invariant mapping, and pseudo-label refinement to mitigate domain discrepancies and enhance cross-domain generalization. Experiments demonstrate substantial gains over baseline methods, with mAP and Rank-1 improvements up to 12% in challenging transfer scenarios. Finally, ViTC-UReID leverages Vision Transformer-based feature encoding and camera-aware proxy learning to boost unsupervised ReID. By integrating global and local attention with camera identity constraints, this method significantly outperforms existing unsupervised approaches on large-scale benchmarks. Comprehensive evaluations across CUHK03, Market-1501, DukeMTMC-reID, and MSMT17 confirm the effectiveness of the proposed methods. The contributions advance ReID research by addressing key limitations in feature learning, domain adaptation, and label noise handling, paving the way for robust deployment in real-world surveillance systems.
Abstract (translated)
人员再识别（ReID）在智能监控系统中扮演着关键角色，通过连接复杂环境中多个摄像头的身份信息来实现这一点。然而，ReID面临着诸如外观变化、领域迁移和标记数据有限等重大挑战。本文提出三种先进方法以提升监督学习、无监督领域适应(UDA)以及完全无监督设置下的ReID性能。 首先，SCM-ReID结合了监督对比学习与混合损失优化（包括分类、中心点、三元组及重心-三元组损失），增强了判别性特征表示，并在Market-1501和CUHK03数据集上实现了最先进的准确性。其次，在UDA背景下，IQAGA和DAPRH通过结合基于GAN的图像增强、领域不变映射以及伪标签优化来缓解域差异并提高跨域泛化能力。实验结果表明这些方法在具有挑战性的迁移场景中相比基准方法在mAP和Rank-1指标上分别提高了高达12%。最后，ViTC-UReID利用基于Vision Transformer的特征编码与相机感知代理学习来提升无监督ReID性能。通过整合全局及局部注意力，并结合相机身份约束，该方法在大规模基准测试中显著超越了现有的无监督方法。 对CUHK03、Market-1501、DukeMTMC-reID和MSMT17的数据集进行全面评估后确认了所提出方法的有效性。这些贡献通过解决特征学习、领域适应及标记噪声处理的关键限制，为ReID研究铺平了道路，并为其在实际监控系统的稳健部署开启了新的方向。
URL
https://arxiv.org/abs/2601.01356
PDF
-
VReID-XFD: Video-based Person Re-identification at Extreme Far Distance Challenge Results
2026-01-04 00:27:16Kailash A. Hambarde, Hugo Proen\c{c}a, Md Rashidunnabi, Pranita Samale, Qiwei Yang, Pingping Zhang, Zijing Gong, Yuhao Wang, Xi Zhang, Ruoshui Qu, Qiaoyun He, Yuhang Zhang, Thi Ngoc Ha Nguyen, Tien-Dung Mai, Cheng-Jun Kang, Yu-Fan Lin, Jin-Hui Jiang, Chih-Chung Hsu, Tam\'as Endrei, Gy\"orgy Cserey, Ashwat RajbhandariAbstract
Person re-identification (ReID) across aerial and ground views at extreme far distances introduces a distinct operating regime where severe resolution degradation, extreme viewpoint changes, unstable motion cues, and clothing variation jointly undermine the appearance-based assumptions of existing ReID systems. To study this regime, we introduce VReID-XFD, a video-based benchmark and community challenge for extreme far-distance (XFD) aerial-to-ground person re-identification. VReID-XFD is derived from the DetReIDX dataset and comprises 371 identities, 11,288 tracklets, and 11.75 million frames, captured across altitudes from 5.8 m to 120 m, viewing angles from oblique (30 degrees) to nadir (90 degrees), and horizontal distances up to 120 m. The benchmark supports aerial-to-aerial, aerial-to-ground, and ground-to-aerial evaluation under strict identity-disjoint splits, with rich physical metadata. The VReID-XFD-25 Challenge attracted 10 teams with hundreds of submissions. Systematic analysis reveals monotonic performance degradation with altitude and distance, a universal disadvantage of nadir views, and a trade-off between peak performance and robustness. Even the best-performing SAS-PReID method achieves only 43.93 percent mAP in the aerial-to-ground setting. The dataset, annotations, and official evaluation protocols are publicly available at this https URL .
Abstract (translated)
跨视角的人员重新识别（Person Re-Identification，简称ReID）在极远距离下从空中视角切换到地面视角时引入了一种独特的操作环境。在这种环境中，严重的分辨率退化、极端的角度变化、不稳定的动作线索以及服装差异共同削弱了现有基于外观假设的重识别系统的有效性。为了研究这一领域，我们提出了VReID-XFD，这是一个针对极远距离（XFD）空中到地面人员重新识别的视频基准和社区挑战。 VReID-XFD来源于DetReIDX数据集，并包含371个身份、11,288条轨迹片段以及超过1175万帧图像。这些图像在高度从5.8米至120米，视角角度从斜侧（30度）到正下方（90度），水平距离高达120米的情况下被捕捉下来。 该基准测试支持空中到空中、空中到地面以及地面到空中的评估，在严格的身份独立划分下进行，并提供了丰富的物理元数据。VReID-XFD-25挑战吸引了来自世界各地的10个团队，提交了数百份作品。系统分析揭示出随着高度和距离增加性能下降的趋势，正下方视角在所有场景下的普遍劣势，以及峰值性能与鲁棒性之间的权衡关系。 即使是最优的方法SAS-PReID，在空中到地面设置中也仅达到了43.93%的平均精度（mAP）。该数据集、标注及官方评估协议可在[提供的链接]处获取。
URL
https://arxiv.org/abs/2601.01312
PDF
-
VisNet: Efficient Person Re-Identification via Alpha-Divergence Loss, Feature Fusion and Dynamic Multi-Task Learning
2026-01-01 11:06:11Anns Ijaz, Muhammad Azeem JavedAbstract
Person re-identification (ReID) is an extremely important area in both surveillance and mobile applications, requiring strong accuracy with minimal computational cost. State-of-the-art methods give good accuracy but with high computational budgets. To remedy this, this paper proposes VisNet, a computationally efficient and effective re-identification model suitable for real-world scenarios. It is the culmination of conceptual contributions, including feature fusion at multiple scales with automatic attention on each, semantic clustering with anatomical body partitioning, a dynamic weight averaging technique to balance classification semantic regularization, and the use of loss function FIDI for improved metric learning tasks. The multiple scales fuse ResNet50's stages 1 through 4 without the use of parallel paths, with semantic clustering introducing spatial constraints through the use of rule-based pseudo-labeling. VisNet achieves 87.05% Rank-1 and 77.65% mAP on the Market-1501 dataset, having 32.41M parameters and 4.601 GFLOPs, hence, proposing a practical approach for real-time deployment in surveillance and mobile applications where computational resources are limited.
Abstract (translated)
人员再识别（ReID）在监控和移动应用领域是非常重要的一个方面，它需要在计算成本极低的情况下保持高精度。虽然最先进的方法提供了很好的准确率，但它们的计算开销较大。为解决这一问题，本文提出了VisNet，这是一种计算效率高且有效的人体再识别模型，适用于现实场景。该模型集成了多个概念贡献，包括多尺度特征融合和自动注意力机制、基于解剖学身体部位划分的语义聚类、用于平衡分类语义正则化的动态权重平均技术以及利用损失函数FIDI改进度量学习任务。 VisNet在不使用并行路径的情况下融合了ResNet50第1至4阶段的特征，通过规则基础伪标签引入空间约束。实验表明，在Market-1501数据集上，VisNet实现了87.05%的Rank-1准确率和77.65%的mAP（平均精度），并且参数量为32.41M，计算复杂度为4.601 GFLOPs。因此，VisNet提出了一种在监控和移动应用中具有实际意义的方法，在这些场景下计算资源有限的情况下仍可实现实时部署。
URL
https://arxiv.org/abs/2601.00307
PDF
-
Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
2025-12-31 17:50:05Zhenyu Cui, Jiahuan Zhou, Yuxin PengAbstract
Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model, focusing on the overall performance of all data. Its main challenge is to avoid the catastrophic forgetting problem of old knowledge while training on new data. Existing L-ReID methods typically re-extract new features for all historical gallery images for inference after each update, known as "re-indexing". However, historical gallery data typically suffers from direct saving due to the data privacy issue and the high re-indexing costs for large-scale gallery images. As a result, it inevitably leads to incompatible retrieval between query features extracted by the updated model and gallery features extracted by those before the update, greatly impairing the re-identification performance. To tackle the above issue, this paper focuses on a new task called Re-index Free Lifelong person Re-IDentification (RFL-ReID), which requires performing lifelong person re-identification without re-indexing historical gallery images. Therefore, RFL-ReID is more challenging than L-ReID, requiring continuous learning and balancing new and old knowledge in diverse streaming data, and making the features output by the new and old models compatible with each other. To this end, we propose a Bidirectional Continuous Compatible Representation (Bi-C2R) framework to continuously update the gallery features extracted by the old model to perform efficient L-ReID in a compatible manner. We verify our proposed Bi-C2R method through theoretical analysis and extensive experiments on multiple benchmarks, which demonstrate that the proposed method can achieve leading performance on both the introduced RFL-ReID task and the traditional L-ReID task.
Abstract (translated)
终身人员重识别（L-ReID）利用连续收集的数据来不断训练和更新重识别模型，重点关注所有数据的整体性能。其主要挑战在于避免在新数据训练过程中出现旧知识的灾难性遗忘问题。现有的L-ReID方法通常会在每次更新后为所有历史图像重新提取特征进行推理，称为“再索引”。然而，由于数据隐私问题以及对大规模历史图库图像重新索引的成本高昂，历史图库数据往往无法直接保存下来。因此，这不可避免地导致了查询特征与更新前的模型提取的历史图库特征之间的不兼容检索，严重影响了重识别性能。 为解决上述问题，本文提出了一项新的任务——无再索引终身人员重识别（RFL-ReID），要求在不重新索引历史图库图像的情况下进行终身人员重识别。因此，相较于L-ReID而言，RFL-ReID更具挑战性，它需要连续学习并在多样化的流数据中平衡新旧知识，并使更新前后的模型输出的特征具有兼容性。 为此，我们提出了双向持续兼容表示（Bi-C2R）框架，以不断更新由旧模型提取的历史图库特征，从而实现高效且兼容性的L-ReID。通过理论分析和在多个基准测试上的广泛实验验证了所提出的Bi-C2R方法的有效性，表明该方法在介绍的RFL-ReID任务以及传统的L-ReID任务上均能取得领先性能。
URL
https://arxiv.org/abs/2512.25000
PDF
-
CropTrack: A Tracking with Re-Identification Framework for Precision Agriculture
2025-12-31 12:59:38Md Ahmed Al Muzaddid, Jordan A. James, William J. BeksiAbstract
Multiple-object tracking (MOT) in agricultural environments presents major challenges due to repetitive patterns, similar object appearances, sudden illumination changes, and frequent occlusions. Contemporary trackers in this domain rely on the motion of objects rather than appearance for association. Nevertheless, they struggle to maintain object identities when targets undergo frequent and strong occlusions. The high similarity of object appearances makes integrating appearance-based association nontrivial for agricultural scenarios. To solve this problem we propose CropTrack, a novel MOT framework based on the combination of appearance and motion information. CropTrack integrates a reranking-enhanced appearance association, a one-to-many association with appearance-based conflict resolution strategy, and an exponential moving average prototype feature bank to improve appearance-based association. Evaluated on publicly available agricultural MOT datasets, CropTrack demonstrates consistent identity preservation, outperforming traditional motion-based tracking methods. Compared to the state of the art, CropTrack achieves significant gains in identification F1 and association accuracy scores with a lower number of identity switches.
Abstract (translated)
在农业环境中进行多目标跟踪（MOT）面临着诸多挑战，包括重复模式、相似物体外观、突然的光照变化以及频繁的遮挡。当前领域的追踪器依赖于对象的运动而非外观来进行关联，但它们难以维持目标在经历频繁且强烈的遮挡时的身份一致性。由于物体外观的高度相似性，基于外观的关联在农业场景中变得复杂。 为了解决这个问题，我们提出了一种新的MOT框架——CropTrack，该框架结合了外观和运动信息。CropTrack集成了增强重排序的外观关联、一对一多对多的外观冲突解决策略以及指数移动平均原型特征库来改进基于外观的关联。在公开的农业MOT数据集上进行评估时，CropTrack展示了持续的身份保持能力，并且优于传统的仅基于运动的方法。与最先进的方法相比，CropTrack在识别F1和关联准确度得分方面实现了显著提升，并且身份切换的数量较少。
URL
https://arxiv.org/abs/2512.24838
PDF
-
Lifelong Domain Adaptive 3D Human Pose Estimation
2025-12-29 20:56:06Qucheng Peng, Hongfei Xue, Pu Wang, Chen ChenAbstract
3D Human Pose Estimation (3D HPE) is vital in various applications, from person re-identification and action recognition to virtual reality. However, the reliance on annotated 3D data collected in controlled environments poses challenges for generalization to diverse in-the-wild scenarios. Existing domain adaptation (DA) paradigms like general DA and source-free DA for 3D HPE overlook the issues of non-stationary target pose datasets. To address these challenges, we propose a novel task named lifelong domain adaptive 3D HPE. To our knowledge, we are the first to introduce the lifelong domain adaptation to the 3D HPE task. In this lifelong DA setting, the pose estimator is pretrained on the source domain and subsequently adapted to distinct target domains. Moreover, during adaptation to the current target domain, the pose estimator cannot access the source and all the previous target domains. The lifelong DA for 3D HPE involves overcoming challenges in adapting to current domain poses and preserving knowledge from previous domains, particularly combating catastrophic forgetting. We present an innovative Generative Adversarial Network (GAN) framework, which incorporates 3D pose generators, a 2D pose discriminator, and a 3D pose estimator. This framework effectively mitigates domain shifts and aligns original and augmented poses. Moreover, we construct a novel 3D pose generator paradigm, integrating pose-aware, temporal-aware, and domain-aware knowledge to enhance the current domain's adaptation and alleviate catastrophic forgetting on previous domains. Our method demonstrates superior performance through extensive experiments on diverse domain adaptive 3D HPE datasets.
Abstract (translated)
三维人体姿态估计（3D HPE）在众多应用中至关重要，从人员再识别和动作识别到虚拟现实。然而，在受控环境中收集的标注3D数据依赖性导致了将其推广至多样化的真实场景中的挑战。现有的域适应（DA）范式，例如针对3D HPE的一般域适应和无源域适应，忽略了目标姿态数据集的非平稳性问题。为了解决这些挑战，我们提出了一项名为终身域适配的三维人体姿态估计的新任务。据我们所知，这是我们首次将终身域适应应用于三维人体姿态估计任务中。在这种终身DA设置下，姿态估计器首先在源域上进行预训练，随后逐步调整以适应不同的目标域。此外，在当前目标域的调适过程中，姿态估计器无法访问源域和所有之前的target domains。 针对3D HPE的终身DA需要克服当前领域的姿势适应挑战，并保留来自先前领域知识的问题，尤其是要解决灾难性遗忘问题。为此，我们提出了一种创新性的生成对抗网络（GAN）框架，该框架结合了三维姿态生成器、二维姿态判别器和三维姿态估计器。此框架有效地缓解了域偏移并使原始姿势与增强后的姿势对齐。 此外，我们构建了一个新颖的3D姿态生成器模式，整合了具有姿态感知、时间感知和领域感知的知识，以提升当前领域的适应性，并减轻在先前领域的灾难性遗忘问题。通过广泛的实验验证，在多样化的三维域适配人体姿态估计数据集上，我们的方法展现出了卓越的表现。
URL
https://arxiv.org/abs/2512.23860
PDF
-
GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification
2025-12-25 02:40:46Suncheng Xiang, Xiaoyang Wang, Junjie Jiang, Hejia Wang, Dahong QianAbstract
Colonoscopic Polyp Re-Identification aims to match the same polyp from a large gallery with images from different views taken using different cameras, which plays an important role in the prevention and treatment of colorectal cancer in computer-aided diagnosis. However, the coarse resolution of high-level features of a specific polyp often leads to inferior results for small objects where detailed information is important. To address this challenge, we propose a novel architecture, named Gated Progressive Fusion network, to selectively fuse features from multiple levels using gates in a fully connected way for polyp ReID. On the basis of it, a gated progressive fusion strategy is introduced to achieve layer-wise refinement of semantic information through multi-level feature interactions. Experiments on standard benchmarks show the benefits of the multimodal setting over state-of-the-art unimodal ReID models, especially when combined with the specialized multimodal fusion strategy.
Abstract (translated)
结肠镜息肉再识别旨在从大量图像库中匹配同一息肉，这些图像是使用不同摄像头从不同角度拍摄的。这一技术在计算机辅助诊断中对预防和治疗大肠癌起着重要作用。然而，特定息肉的高级特征通常分辨率较低，这导致对于细节信息至关重要的小对象识别效果不佳。为了解决这一挑战，我们提出了一种新颖的架构，名为门控渐进融合网络（Gated Progressive Fusion network），该架构通过使用全连接方式中的门来选择性地融合来自多个级别的特征，以实现息肉再识别。在此基础上，引入了门控渐进融合策略，通过多层次特征交互实现语义信息逐层细化。 在标准基准上的实验表明，多模态设置相较于最先进的单模态再识别模型具有优势，尤其是在结合专门设计的多模态融合策略时效果更佳。
URL
https://arxiv.org/abs/2512.21476
PDF
-
SALP-CG: Standard-Aligned LLM Pipeline for Classifying and Grading Large Volumes of Online Conversational Health Data
2025-12-25 01:52:46Yiwei Yan, Hao Li, Hua He, Gong Kai, Zhengyi Yang, Guanfeng LiuAbstract
Online medical consultations generate large volumes of conversational health data that often embed protected health information, requiring robust methods to classify data categories and assign risk levels in line with policies and practice. However, existing approaches lack unified standards and reliable automated methods to fulfill sensitivity classification for such conversational health data. This study presents a large language model-based extraction pipeline, SALP-CG, for classifying and grading privacy risks in online conversational health data. We concluded health-data classification and grading rules in accordance with GB/T 39725-2020. Combining few-shot guidance, JSON Schema constrained decoding, and deterministic high-risk rules, the backend-agnostic extraction pipeline achieves strong category compliance and reliable sensitivity across diverse LLMs. On the MedDialog-CN benchmark, models yields robust entity counts, high schema compliance, and accurate sensitivity grading, while the strongest model attains micro-F1=0.900 for maximum-level prediction. The category landscape stratified by sensitivity shows that Level 2-3 items dominate, enabling re-identification when combined; Level 4-5 items are less frequent but carry outsize harm. SALP-CG reliably helps classify categories and grading sensitivity in online conversational health data across LLMs, offering a practical method for health data governance. Code is available at this https URL.
Abstract (translated)
在线医疗咨询生成了大量的对话健康数据，这些数据中往往包含受保护的健康信息，需要有强大的方法来分类数据类别并根据政策和实践为其分配风险级别。然而，现有的方法缺乏统一的标准和可靠的自动化手段来进行此类对话健康数据的敏感性分类。本研究提出了一种基于大型语言模型的提取管道SALP-CG，用于在线对话健康数据中隐私风险的分类与分级。我们依照GB/T 39725-2020标准制定了健康数据分类和分级规则。结合少量样本指导、JSON Schema约束解码及确定性高风险规则，该后台无关提取管道在不同大型语言模型上实现了强大的类别合规性和可靠的敏感度。 在MedDialog-CN基准测试中，模型显示了稳健的实体计数、高水平的模式符合以及准确的敏感级别分级。最强力的模型达到了最大级预测的微平均F1值为0.900。根据敏感性对类别的分布情况进行细分后可以发现，2-3级别的条目占主导地位，并且在结合使用时能够实现再识别；4-5级别的条目较少但危害巨大。 SALP-CG可靠地帮助跨大型语言模型在线对话健康数据分类和分级，为健康管理提供了一种实用的方法。代码可以在提供的链接中获取。
URL
https://arxiv.org/abs/2601.09717
PDF
-
Beyond Weight Adaptation: Feature-Space Domain Injection for Cross-Modal Ship Re-Identification
2025-12-24 02:30:23Tingfeng Xian, Wenlve Zhou, Zhiheng Zhou, Zhelin LiAbstract
Cross-Modality Ship Re-Identification (CMS Re-ID) is critical for achieving all-day and all-weather maritime target tracking, yet it is fundamentally challenged by significant modality discrepancies. Mainstream solutions typically rely on explicit modality alignment strategies; however, this paradigm heavily depends on constructing large-scale paired datasets for pre-training. To address this, grounded in the Platonic Representation Hypothesis, we explore the potential of Vision Foundation Models (VFMs) in bridging modality gaps. Recognizing the suboptimal performance of existing generic Parameter-Efficient Fine-Tuning (PEFT) methods that operate within the weight space, particularly on limited-capacity models, we shift the optimization perspective to the feature space and propose a novel PEFT strategy termed Domain Representation Injection (DRI). Specifically, while keeping the VFM fully frozen to maximize the preservation of general knowledge, we design a lightweight, learnable Offset Encoder to extract domain-specific representations rich in modality and identity attributes from raw inputs. Guided by the contextual information of intermediate features at different layers, a Modulator adaptively transforms these representations. Subsequently, they are injected into the intermediate layers via additive fusion, dynamically reshaping the feature distribution to adapt to the downstream task without altering the VFM's pre-trained weights. Extensive experimental results demonstrate the superiority of our method, achieving State-of-the-Art (SOTA) performance with minimal trainable parameters. For instance, on the HOSS-ReID dataset, we attain 57.9\% and 60.5\% mAP using only 1.54M and 7.05M parameters, respectively. The code is available at this https URL.
Abstract (translated)
跨模态船只再识别（CMS Re-ID）对于全天候海上目标追踪至关重要，但其核心挑战在于显著的模态差异。主流解决方案通常依赖于显式的模态对齐策略；然而，这种范式严重依赖于构建大规模配对数据集进行预训练。为了解决这一问题，在柏拉图表征假设的基础上，我们探讨了视觉基础模型（VFMs）在弥合模态差距方面的潜力。鉴于现有的通用参数高效微调（PEFT）方法在权重空间内操作时在容量有限的模型上表现不佳，我们将优化视角转向特征空间，并提出了一种新的PEFT策略，称为域表征注入（DRI）。具体而言，在保持VFMs完全冻结以最大限度地保留一般知识的同时，我们设计了一个轻量级、可学习的Offset Encoder来从原始输入中提取富含模态和身份属性的特定领域表示。基于不同层间中间特征的上下文信息，一个调制器会自适应地转换这些表示。随后，通过加性融合将它们注入到中间层，动态重塑特征分布以适应下游任务，而不改变VFMs的预训练权重。 广泛的实验结果表明了我们方法的优越性，在使用最少可训练参数的情况下达到了最先进的性能（SOTA）。例如，在HOSS-ReID数据集上，我们分别使用1.54M和7.05M个参数实现了57.9%和60.5%mAP。代码可在[提供链接处]获得。
URL
https://arxiv.org/abs/2512.20892
PDF
-
Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation
2025-12-22 04:53:40Connor Kilrain, David Carlyn, Julia Chae, Sara Beery, Wei-Lun Chao, Jianyang GuAbstract
The rise of personalized generative models raises a central question: how should we evaluate identity preservation? Given a reference image (e.g., one's pet), we expect the generated image to retain precise details attached to the subject's identity. However, current generative evaluation metrics emphasize the overall semantic similarity between the reference and the output, and overlook these fine-grained discriminative details. We introduce Finer-Personalization Rank, an evaluation protocol tailored to identity preservation. Instead of pairwise similarity, Finer-Personalization Rank adopts a ranking view: it treats each generated image as a query against an identity-labeled gallery consisting of visually similar real images. Retrieval metrics (e.g., mean average precision) measure performance, where higher scores indicate that identity-specific details (e.g., a distinctive head spot) are preserved. We assess identity at multiple granularities -- from fine-grained categories (e.g., bird species, car models) to individual instances (e.g., re-identification). Across CUB, Stanford Cars, and animal Re-ID benchmarks, Finer-Personalization Rank more faithfully reflects identity retention than semantic-only metrics and reveals substantial identity drift in several popular personalization methods. These results position the gallery-based protocol as a principled and practical evaluation for personalized generation.
Abstract (translated)
个性化生成模型的兴起引发了一个核心问题：我们应该如何评估身份保持？给定一个参考图像（例如某人的宠物），我们期望生成的图像是以精确细节保留主体的身份特征。然而，当前的生成评估指标强调了参考图像和输出图像之间的整体语义相似性，并忽略了这些细微的区别性细节。为此，我们引入了一种针对身份保持量化的评估协议——Finer-Personalization Rank。 与传统的成对相似度相比，Finer-Personalization Rank 采用了一个排名视角：它将每个生成的图像视为一个查询，在由视觉上类似的现实图像组成的、包含身份标签的图库中进行检索。通过使用诸如平均精度等检索指标来衡量性能，得分越高表示特定于身份的独特细节（例如独特的头部标记）得以保留。 我们从多个粒度层面上评估了身份——从细微类别（如鸟类种类、汽车型号）到个体实例（如再识别）。在 CUB 数据集、Stanford Cars 和动物 Re-ID 基准测试中，Finer-Personalization Rank 比仅基于语义的指标更真实地反映了身份保持，并且揭示了几个流行的个性化方法中存在的显著的身份漂移现象。 这些结果将基于图库的协议确立为个性化工作者评估的一个原理性和实用性的标准。
URL
https://arxiv.org/abs/2512.19026
PDF
