This work proposes MDCRNet, a Multi-scale Decomposed Convolution Refinement Network that enhances cross-modal feature learning and discriminative metric learning, and develops a Joint Discriminative Metric Loss incorporating a novel Granularity Discriminative Loss (GDL).
Abstract
Visible-infrared person re-identification (VI-ReID) suffers from cross-modal discrepancies and limited discriminative capabilities, leading to suboptimal recognition performance. Current approaches exhibit limitations in semantic mining, cross-modal fusion and feature constraints. To tackle these challenges, we propose MDCRNet, a Multi-scale Decomposed Convolution Refinement Network that enhances cross-modal feature learning and discriminative metric learning. Specifically, we introduce a Hierarchical Learning Module (HLM) containing four Hierarchical Decomposed Convolution Attention (HDCA) modules, each equipped with lightweight channel attention and multi-scale spatial perception blocks to capture multi-scale spatial dependencies. Moreover, we develop a Joint Discriminative Metric Loss (JDML) incorporating a novel Granularity Discriminative Loss (GDL) that simultaneously optimizes intra-identity compactness and inter-identity separability across modalities. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate that MDCRNet achieves state-of-the-art performance on both benchmarks. Code is available at https://github.com/Kevin-zms/MDCRNet.
To address the performance degradation of person re-identification (ReID) under complex lighting and day-night conditions, this study proposes a novel dual-path convolution based multi-scale feature alignment (DCMFA) network. The network mainly focuses on addressing the challenges of modality discrepancy and feature alignment between visible and infrared images. First, to cope with feature deformation in persons caused by external factors in both modalities, we design a dual-path convolution (DPCon) layer. Secondly, to further alleviate feature loss caused by scale variation, we construct a multi-scale feature aggregation (MSFA) module by stacking DPCon layers of different depths and incorporating an attention mechanism to effectively aggregate key multi-scale information and suppress redundancy. Finally, to enable more effective alignment of multi-scale features across the two modalities, we propose a feature mapping and alignment operations (FMAO) module. Experimental results on three publicly available cross-modal visible-infrared person re-identification (VI-ReID) datasets demonstrate that our DCMFA network significantly outperforms existing mainstream methods in terms of recognition accuracy. Specifically, on the SYSU-MM01 dataset, our method achieves a Rank-1 accuracy of 83.74% in the single-shot setting and 89.47% in the multi-shot setting.
B. Huang, Bin Chen, Tian-Ran Sun et al.· 電腦學刊· 0 citations
Cross-modal person re-identification between visible and infrared domains remains a challenging problem due to significant modality gaps. This paper presents a novel approach termed Intermediate Shared Feature Network (ISFNet) that explicitly addresses this issue by exploiting intermediate feature representations within a dual-stream backbone. Unlike conventional methods that primarily focus on final-layer features, ISFNet introduces two complementary components: a Multi-layer Feature Cascade Module (MFCM) that aggregates discriminative features across different network stages, and a Dual Feature Generation Module (DFGM) that creates diverse intermediate representations through Instance-Batch Normalization variants. By integrating these modules, ISFNet effectively bridges the cross-modal gap and improves matching accuracy. Comprehensive experiments on the SYSU-MM01 and RegDB datasets demonstrate that the proposed method achieves competitive performance against state-of-the-art approaches, with noticeable improvements in both Rank-1 accuracy and mean average precision.
Aobo Fan, Wangmeng Wang, Zhixin Tie et al.· Electronics· 0 citations
A Progressively Biased Split Vision Transformer (PBSVT) is proposed, which combines a split ViT backbone with progressive bias training to gradually reduce RGB-dominant bias while preserving modality-shared structure and demonstrates the effectiveness of progressive modality transition for robust VI-ReID representation learning.
Mengru Jiao, Xin-Yue Xu, Junfeng Zhang· International journal of pat...· 0 citations
Visible-infrared person re-identification (VI-ReID) is an important technique for around-the-clock person matching, and its primary challenge arises from substantial cross-modal discrepancies. To address this challenge, we propose a Decoupled Information-Guided Cross-Modal Alignment (DIGCA) framework organized into three stages: multi-scale feature modeling, partial functional decoupling, and guided cross-modal alignment. First, a Hierarchical Context Extractor (HCE) aggregates multi-scale contextual information through dilated convolutions and residual connections to enrich the initial identity representation. Second, a Multi-Branch Unified Encoder (MBUE) organizes complementary feature streams through parallel global-relation and local-spatial modeling. The resulting representations exhibit different information tendencies and promote partial functional decoupling between identity-related and modality-related information. Finally, the Decoupled Information-Guided Cross-Modal Alignment (DIG-CMA) module refines the two streams with channel and spatial attention and integrates them through cross-attention. Under the joint optimization objective, the resulting representations support cross-modal alignment. Experiments on SYSU-MM01, RegDB, and LLCM show that DIGCA achieves competitive overall performance compared with recent VI-ReID methods, providing empirical support for the effectiveness of the proposed decoupling-guided alignment strategy in cross-modal identity matching.
Visible-infrared person re-identification (VI-ReID) remains challenging due to severe spectral discrepancy and local cross-modal misalignment between visible and infrared images. Most existing methods alleviate this discrepancy through middle- or late-stage feature alignment, but modality-specific shallow features may have already accumulated spectral bias and local correspondence errors before shared representations are formed. In this paper, we argue that VI-ReID should be treated as an early cross-modal correspondence learning problem rather than only a late embedding alignment problem. To this end, we propose \textbf{CMIA-Net}, a framework that establishes bidirectional visible-infrared interaction at shallow backbone stages. Its core module, \textbf{Cross-Modal Interaction Attention (CMIA)}, enables visible and infrared feature maps to exchange complementary local information before deep semantic aggregation, thereby reducing progressive stream divergence. To stabilize early interaction, we further introduce \textbf{Spectral-Invariant Augmentation (MC-Aug)} to suppress over-reliance on visible-spectrum cues and a \textbf{Bi-directional Hetero-Center Learning (BHCT)} loss to improve class-center-level cross-modal compactness and inter-class separability. Experiments on RegDB and SYSU-MM01 show that CMIA-Net achieves strong performance on RegDB and the SYSU-MM01 indoor-search protocol, while remaining competitive under the more challenging SYSU-MM01 all-search setting. Specifically, CMIA-Net obtains 94.09\% Rank-1 accuracy and 90.74\% mAP in the RegDB visible-to-thermal setting, and 66.67\% Rank-1 accuracy and 58.12\% mAP in the SYSU-MM01 all-search setting.
Unknown authors· Engineering Research Express· 0 citations
Person re-identification (Re-ID) aims to retrieve the same person across non-overlapping cameras. Despite recent progress, Re-ID remains highly challenging due to high inter-class similarity in large-scale datasets and drastic intra-class variations in cross-platform scenarios (e.g., drones and wearable cameras). While Transformers have been introduced to Re-ID for their superior long-range dependency modeling and robustness against global appearance morphology changes, they often struggle to capture fine-grained discriminative local features due to the inherent properties of the self-attention mechanism. To address this, we propose a Reinforced-Transformer (RT) architecture designed to recover and reinforce these critical local details. Specifically, we develop a Detail Retention Module (DRM) to preserve salient local information while enhancing the interaction between local and global features. Building on this, a Multi-Detail Recovery Module (MDRM) is introduced to progressively restore local features from both coarse-to-fine and fine-to-coarse perspectives. Extensive experiments on four large-scale benchmarks and a mixed aerial-ground dataset demonstrate that our method achieves state-of-the-art (SOTA) or highly competitive performance across different benchmarks.
Meifeng Liu, Hua Han, A. A. M. Muzahid et al.· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
