Homogeneous and Heterogeneous Consistency progressive Re-ranking for Visible-Infrared Person Re-identification

Yiming Wang

cs.CVMar 17, 2026

Homogeneous and Heterogeneous Consistency progressive Re-ranking for Visible-Infrared Person Re-identification

Authors: Yiming Wang

Abstract

Visible-infrared person re-identification faces greater challenges than traditional person re-identification due to the significant differences between modalities. In particular, the differences between these modalities make effective matching even more challenging, mainly because existing re-ranking algorithms cannot simultaneously address the intra-modal variations and inter-modal discrepancy in cross-modal person re-identification. To address this problem, we propose a novel Progressive Modal Relationship Re-ranking method consisting of two modules, called heterogeneous and homogeneous consistency re-ranking(HHCR). The first module, heterogeneous consistency re-ranking, explores the relationship between the query and the gallery modalities in the test set. The second module, homogeneous consistency reranking, investigates the intrinsic relationship within each modality between the query and the gallery in the test set. Based on this, we propose a baseline for cross-modal person re-identification, called a consistency re-ranking inference network (CRI). We conducted comprehensive experiments demonstrating that our proposed re-ranking method is generalized, and both the re-ranking and the baseline achieve state-of-the-art performance.

Figures & tables

Figure 1: The crosshair represents the center of the same identity, the same color indicates the same identity, and the circles and rectangles represent the two modalities. The arrows signify the process of reducing or increasing distances. Currently, the re-ranking methods applied to visible-infrared ReID consist of a single-stage re-ranking process, including only homogeneous re-ranking or heterogeneous re-ranking. The re-ranking method we propose includes Homogeneous Consistency Re-ranking and Heterogeneous Consistency Re-ranking.

Figure 2: The pipeline of the proposed network. The network structure processes the input visible and infrared images through ResNet to extract features, followed by a BN (Batch Normalization) layer for normalization, and finally, computes the loss function. During the testing phase, HHCR first concatenates the test set to compute the original similarity matrix $A_{sim}^{ori}$ . Then, it separately calculates Homogeneous and Heterogeneous Consistency Re-ranking. Finally, the initial similarity matrix is filtered and summed, resulting in the final similarity matrix. The yellow line represents the noise filtering step for the original features, while the blue line indicates the noise filtering step for the original features after HECR graph convolution processing.

methods	SYSU		RegDB		LLCM
methods	Rank1	mAP1	Rank1	mAP1	Rank1	mAP1
k-reciprocal	83.22	80.60	86.75	87.41	72.70	70.99
GNN	81.96	83.36	86.31	89.30	76.19	75.43
ECN	83.93	85.04	87.28	88.63	74.88	72.89
Ours	83.98	85.32	89.3	89.9	80.6	76.8

Table 1: Comparison of Other Re-Ranking Methods and HHCR on Various Cross-Modal Person Re-Identification Datasets.

methods	SYSU		RegDB		LLCM
methods	mAP(%)	Rank1(%)	mAP(%)	Rank1(%)	mAP(%)	Rank1(%)
AGW	87.75	88.44	88.59	90.50	-	-
Ours	87.31	88.26	96.54	97.19	-	-
Yours	-	-	-	-	-	-
Ours	-	-	-	-	-	-

Table 2: Comparison of Applying HHCR and Without HHCR in Other V-I ReID Models.

Methods	All-Search				Indoor-Search
	Single-Shot		Multi-Shot		Single-Shot		Multi-Shot
	Rank1	mAP	Rank1	mAP	Rank1	mAP	Rank1	mAP
Zero-Padding [ 15 ]	14.80	15.95	19.13	10.89	20.58	26.92	24.43	18.86
cmGAN [ 17 ]	26.97	27.80	31.49	22.27	31.63	42.19	37.00	32.76
JSIA-ReID [ 5 ]	38.10	36.90	45.10	29.50	43.80	52.90	52.70	42.70
AlignGAN [ 8 ]	42.40	40.70	51.50	33.90	45.90	54.30	57.10	45.30

Table 3: Comparison with State-of-the-Art Methods on SYSU-MM01.

methods	VIS to IR		IR to VIS
methods	Rank1	mAP	Rank1	mAP1
Zero-Padding [ 15 ]	17.75	18.90	16.63	17.82
JSIA-ReID [ 5 ]	48.50	49.30	48.10	48.90
AlignGAN [ 8 ]	57.90	53.60	56.30	53.40
AGW [ 21 ]	70.05	66.37	70.49	65.9
cm-SSFT [ 20 ]	72.30	72.90	71.00	71.70

Table 4: Comparison with State-of-the-Art Methods on Regdb.

methods	IR to VIS		VIS to IR
methods	Rank1	mAP	Rank1	mAP
DDAG [ 8 ]	40.3	48.4	48.0	52.3
AGW [ 21 ]	43.6	51.8	51.5	55.3
LbA [ 28 ]	43.8	53.1	50.8	55.6
CAJ [ 37 ]	48.8	56.6	56.5	59.8
DART [ 38 ]	52.2	59.8	60.4	63.2

Table 5: Comparison with State-of-the-Art Methods on LLCM.

ICR	HR	HR w/o RTF	RegDB		SYSU		LLCM
ICR	HR	HR w/o RTF	Rank1	mAP	Rank1	mAP1	Rank1	mAP1
			86.3	83.7	66.18	64.31	63.09	49.07
✓			85.6	89.0	64.34	72.02	71.1	66.57
✓	✓		90.7	92.9	83.98	85.32	75.87	75.24
✓		✓	91.8	93	80.49	82.59	80.6	76.8

Table 6: The impact of Ranked Transposition Filtering, Transposition Filtering, Intrinsic Consistency Reranking, and Hetero-spectral Re-ranking on performance.

Figure 3: Comparison of Top 10 Retrieval Results with and without PMRR.

Visible-Infrared Person Re-Identification

See all 13 papers

Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching
Jul 21, 2026Xin Xu, Shuhao Zhan, Wei Liu +3Missing-Modality Learning Cross-Modal Representation Learning
School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430065, Hubei, China. · Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan, 430081, Hubei, China. · School of Computer Science, Wuhan University, Wuhan, 430079, Hubei, China. +2
Multi-scale Decomposed Convolution Refinement Network for Visible-Infrared Person Re-Identification
Aug 17, 2026Mingsheng Zheng, Zirui Jiang, Bo Liu +3Visible-Infrared Person Re-Identification Person Re-Identification
School of Computer Science and Technology, Xinjiang University, Urumqi, Xinjiang 830046, China · Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University, Urumqi, Xinjiang 830046, China
BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification
Mar 15, 2026Haoxuan Xu, Guanglin NiuVisible-Infrared Person Re-Identification Person Re-Identification
School of Artificial Intelligence, Beihang University

Jul 21, 2026J/K move · Enter open · S save

Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching

Xin Xu, Shuhao Zhan, Wei Liu, Zheng Wang+2

School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430065, Hubei, China. · Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan, 430081, Hubei, China. · School of Computer Science, Wuhan University, Wuhan, 430079, Hubei, China.+2

Missing-Modality Learning Cross-Modal Representation Learning Cross-Modal Retrieval Person Re-Identification Visible-Infrared Person Re-Identification

Open paper AskPDF arXiv

Visible-Infrared Person Re-Identification (VI-ReID) operates under a closed-world assumption, where queries and galleries are from heterogeneous modalities. However, in open-world scenarios, both sets are likely to contain homogeneous and heterogeneous modality images. A query may consist of visible-only, infrared-only, or mixed-modality images, while galleries present multi-modal images over long-term collection. Under these conditions, VI-ReID methods, built on a heterogeneous-modality retrieval paradigm, suffer from three trustworthiness challenges: matching conflicts due to high homogeneous-modality similarity, interference from modality uncertainty, and robustness degradation induced by unknown modality combinations. They fail to meet the requirements of trustworthy visual recognition in reliability, consistency, and dynamic adaptability. To address these challenges, we formalize the Visible-Infrared Modality-Incomplete Re-Identification (VIMI-ReID) task. We reorganize existing datasets to construct the SYSU-VIMI and RegDB-VIMI benchmarks. The unpredictable modality combinations and inherent similarity of homogeneous-modality samples in VIMI-ReID cause a significant performance drop in existing VI-ReID methods. We propose the Modality Adaptive Matching Transformer (MAMT). It employs a Divergence Transformer Module (DTM) and a Shared Transformer Module (STM) to extract modality-specific and modality-shared features, respectively. Guided by a divergence loss, the DTM enriches modality-specific features with modality-style information to enhance discriminability within the same modality. A Modality Adaptive Matching Module (MAM) dynamically fuses features according to the query-gallery modality relationship, enabling stable matching under arbitrary and uncertain modality conditions. Extensive experiments on the VIMI benchmarks demonstrate the effectiveness and adaptability of MAMT.

Abstract

Visible-Infrared Person Re-Identification

Explore similar work

Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching

Multi-scale Decomposed Convolution Refinement Network for Visible-Infrared Person Re-Identification

BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification