Prototype Matters: Modality-unified Prototype Self-distillation for Unsupervised Visible-infrared Person Re-identification

• URL: http://arxiv.org/abs/2609.11514v1
• Date: Thu, 10 Sep 2026 13:19:00 GMT
• Title: Prototype Matters: Modality-unified Prototype Self-distillation for Unsupervised Visible-infrared Person Re-identification
• Abstract summary: Estimating reliable cross-modality association is crucial to unsupervised visible-infrared person re-ID.<n>We propose a novel framework for cross-modality learning by well exploitation of prototypes.
• Score: 8.26633510662346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Estimating reliable cross-modality association is crucial to unsupervised visible-infrared person re-ID. While optimal transport is shown to be a practical solution for cross-modality association, it suffers from the rigidness of hard label assignment without considering the impact of cluster noise. Moreover, enforcing only cross-modality contrast is also suboptimal, as it fails to jointly optimize the similarity relation within and across modality. In this paper, we propose a novel framework for cross-modality learning by well exploitation of prototypes: First, instead of contrasting with cross-modality prototypes, we show that modality-unified prototypical contrast facilitates better modality invariance by jointly and simultaneously optimizing similarity relation within and across-modality. Taking self-prototype as a steady teacher, we further refine the instance-prototype online relation through prototype-guided self-distillation. The two components are optimized in a unified framework, leading to a simple yet effective model. On standard VI-ReID benchmarks, we perform extensive comparison and analysis, validating the effectiveness of our proposed method. Code is available at: https://github.com/Terminator8758/PoSeD.

Related papers

• Traits Run Deeper: Trait-Specific Asymmetric Fusion for Personality Assessment [53.50824432699408]
  Traits Run Deeper is a novel personality assessment framework.<n>It consists of three components: the Multimodal Foundation Representation (MFR), the Trait-Specific Modality Fusion (TSMF) and the Distribution-Calibrated Personality Regression (DCPR)
  arXiv  Detail & Related papers  (2026-06-09T06:38:36Z)
• COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations [73.40758654107724]
  We introduce a COMposed image retrieval network guided by By attrIbute-based NEighbor Relations (COMBINER)<n>Specifically, we first design an Adaptive Semantic Disentanglement module, which is capable of disentangling attribute features.<n> Secondly, we propose a Unified Prototype-based Composition module, which can construct cross-modal unified prototypes.<n>Finally, we introduce a Dual Relations Modeling module, which can mine pairwise and neighbor relations based on attribute similarity.
  arXiv  Detail & Related papers  (2026-06-03T08:43:51Z)
• Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models [54.597200388738656]
  Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples.<n>We show that many can be written under a common framework, which we call reward score matching (RSM)
  arXiv  Detail & Related papers  (2026-04-19T12:47:52Z)
• Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification [14.343677160918723]
  Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation.<n> estimating reliable cross-modality association is a major challenge in USVI-ReID.<n>This paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning.
  arXiv  Detail & Related papers  (2025-12-08T17:42:28Z)
• Dual-Granularity Cross-Modal Identity Association for Weakly-Supervised Text-to-Person Image Matching [7.1469465755934785]
  Weakly supervised text-to-person image matching is a crucial approach to reducing models' reliance on large-scale manually labeled samples.<n>We propose a dual-granularity identity association mechanism to predict complex one-to-many identity relationships.<n> Experimental results demonstrate that the proposed method substantially boosts cross-modal matching accuracy.
  arXiv  Detail & Related papers  (2025-07-09T10:59:13Z)
• SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuning [17.104905795008555]
  We propose a framework named Selective Cross-modal Prompt Tuning (SCING) that enhances cross-modal alignment and robustness against real-worlds.<n>Our framework eliminates heavy adapters while maintaining efficient inference, achieving an optimal trade-off between performance and computational overhead.
  arXiv  Detail & Related papers  (2025-07-01T07:21:31Z)
• Mix-Modality Person Re-Identification: A New and Practical Paradigm [20.01921944345468]
  We propose a new and more practical mix-modality retrieval paradigm.<n>Existing visible-infrared person re-identification (VI-ReID) methods have achieved some results in the bi-modality mutual retrieval paradigm.<n>This paper proposes a Mix-Modality person re-identification (MM-ReID) task, explores the influence of modality mixing ratio on performance, and constructs mix-modality test sets for existing datasets.
  arXiv  Detail & Related papers  (2024-12-06T02:19:57Z)
• Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification [39.70083261306122]
  Unsupervised visible infrared person re-identification (USVI-ReID) is a challenging retrieval task that aims to retrieve cross-modality pedestrian images without using any label information. In this paper, we first deduce an optimization objective for unsupervised VI-ReID based on the mutual information between the model's cross-modality input and output. Under their guidance, we design a loop iterative training strategy alternating between model training and cross-modality matching.
  arXiv  Detail & Related papers  (2024-07-17T17:32:07Z)
• Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement [53.044703127757295]
  Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset. We propose a Dual Optimal Transport Label Assignment (DOTLA) framework to simultaneously assign the generated labels from one modality to its counterpart modality. The proposed DOTLA mechanism formulates a mutual reinforcement and efficient solution to cross-modality data association, which could effectively reduce the side-effects of some insufficient and noisy label associations.
  arXiv  Detail & Related papers  (2023-05-22T04:40:30Z)
• Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID [56.573905143954015]
  We propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters. Under such a supervisory signal, a Modality-Specific and Modality-Agnostic (MSMA) contrastive learning framework is proposed to align features jointly at a cluster-level. Experiments on the public SYSU-MM01 and RegDB datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2023-05-22T03:27:46Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.