Cross-modality Discrepancy Research Articles

DMANet: Dual-modality alignment network for visible–infrared person re-identification

Visible–infrared person re-identification (VI-ReID) is a challenging retrieval task, which aims to match the same pedestrian between visible and infrared modalities. Most existing works achieve performance gains by solving the problem of the inherent cross-modality discrepancies. However, they cannot fully mine the modality information and lead to a poor generalization. In addition, the pedestrian images are unable to align well due to the large inter- and intra- class variations. To tackle the above limitations, we propose a novel dual-modality alignment network (DMANet) for VI-ReID. The core idea of our work is to develop multi-granularity features mutual learning (MGFML) for inadequate perception of modalities information, and to solve modality difference by proposing inter- and intra- modality alignment module (IIMA). Specifically, firstly, an effective multi-granularity features mutual learning module is proposed to mine the multi-granularity features, which combines the domain alignment and self-distillation to relieve modality discrepancy. Further, the maximum mean discrepancy loss and mutual learning loss are presented to enhance the identity-aware ability of the DMANet. Secondly, an effective inter- and intra- modality alignment module is presented to explore the potential alignment relation of inter- and intra- modalities. Finally, joint learning mechanism of multi-granularity features and modality alignment is utilized to improve the VI-ReID accuracy. Extensive experiments on mainstream benchmarks demonstrate that our method is superior to the state-of-the-art methods.

Exploring modality enhancement and compensation spaces for visible-infrared person re-identification

Visible-infrared person re-identification (VI-ReID) is a challenging task in computer vision due to the substantial modality gaps between visible and infrared images. The currently existing approaches can improve performance by addressing cross-modality discrepancies, but they often fail to generate compensation features that fully utilize the unique information present in each modality. Additionally, these methods mainly focus on pixel-level fusion of images, disregarding the challenge of modality misalignment. To address these issues, we propose a novel visible-infrared person re-identification method that explores modality enhancement and compensation spaces to extract more discriminative modality information. Furthermore, we introduce a modality mutual guidance strategy incorporating identity information mutual learning loss and modality-guided alignment loss, which can effectively leverage learned identity-related feature to guide alignment between visible and infrared modalities. Extensive experiments on public datasets demonstrate the significant superiority of our proposed method over existing state-of-the-art approaches.

Learning to disentangle and fuse for fine-grained multi-modality ship image retrieval

Multi-modality ship image retrieval aims to retrieve ship images from a large dataset, encompassing various modalities, when provided with a query ship image. One of the key challenges is addressing intra-modality variations and cross-modality discrepancies resulting from complex image content and different types of imaging systems. Current multi-modality retrieval methods primarily focus on extracting heterogeneous features from diverse modalities and mapping them into a shared feature space. However, these methods fail to determine the meaningfulness of the extracted features for retrieval tasks, as the features extracted across different modalities exhibit highly complex interactions. To overcome this limitation, we propose a novel framework, dubbed Disentangled Fusion Network (DFN), to decompose ship images into attribute and identity features, capturing modality-specific details and facilitating ship identification. This is achieved through an image disentanglement and fusion module, separating features across different modalities and converting the challenging multi-modality retrieval problem into a more manageable single-modality problem. To enable fine-grained retrieval, a region mining module identifies discriminative areas within ship images. The training process utilizes a bilevel optimization strategy to learn parameters, optimizing both image fusion and retrieval. Extensive experiments conducted on a publicly available multi-modality ship image dataset demonstrate the superior performance of the proposed DFN in image fusion and retrieval tasks.

A Generative-Based Image Fusion Strategy for Visible-Infrared Person Re-Identification

Cross-modality person re-identification task is a challenging task aiming to recognize images of the same identity between different modalities. To alleviate the cross-modality discrepancies between images, existing approaches mainly guide models to mine modality invariant features. Although those approaches are effective, they lose the modality-specific features that include important information beneficial to VI-ReID. Therefore, some approaches are using generative adversarial networks to compensate for modality information. However, the quality of images generated by these methods is usually poor, and most of them focus only on the learning of modality-sharable features. To solve these problems, this paper proposes a generative-based cross-modality image fusion strategy (GC-IFS), which can generate high-quality cross-modality paired images and fuse the information of the two modalities. Firstly, considering the importance of the identity discriminative information of the generated image, we propose a contrastive-learning image generation (CLIG) network to generate cross-modality paired images. Meanwhile, to fully integrate and utilize the information of the two modalities and eliminate the influence of cross-modality discrepancies, we design a part-based dual multi-modality feature fusion (P-DMFF) module to extract the unified feature representation. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate that our strategy outperforms the state-of-the-art methods for the VI-ReID task.

Global-Local Multiple Granularity Learning for Cross-Modality Visible-Infrared Person Reidentification.

Cross-modality visible-infrared person reidentification (VI-ReID), which aims to retrieve pedestrian images captured by both visible and infrared cameras, is a challenging but essential task for smart surveillance systems. The huge barrier between visible and infrared images has led to the large cross-modality discrepancy and intraclass variations. Most existing VI-ReID methods tend to learn discriminative modality-sharable features based on either global or part-based representations, lacking effective optimization objectives. In this article, we propose a novel global-local multichannel (GLMC) network for VI-ReID, which can learn multigranularity representations based on both global and local features. The coarse- and fine-grained information can complement each other to form a more discriminative feature descriptor. Besides, we also propose a novel center loss function that aims to simultaneously improve the intraclass cross-modality similarity and enlarge the interclass discrepancy to explicitly handle the cross-modality discrepancy issue and avoid the model fluctuating problem. Experimental results on two public datasets have demonstrated the superiority of the proposed method compared with state-of-the-art approaches in terms of effectiveness.

RoMo: Robust Unsupervised Multimodal Learning With Noisy Pseudo Labels.

The rise of the metaverse and the increasing volume of heterogeneous 2D and 3D data have created a growing demand for cross-modal retrieval, enabling users to query semantically relevant data across different modalities. Existing methods heavily rely on class labels to bridge semantic correlations; however, collecting large-scale, well-labeled data is expensive and often impractical, making unsupervised learning more attractive and feasible. Nonetheless, unsupervised cross-modal learning faces challenges in bridging semantic correlations due to the lack of label information, leading to unreliable discrimination. In this paper, we reveal and study a novel problem: unsupervised cross-modal learning with noisy pseudo-labels. To address this issue, we propose a 2D-3D unsupervised multimodal learning framework that leverages multimodal data. Our framework consists of three key components: 1) Self-matching Supervision Mechanism (SSM) warms up the model to encapsulate discrimination into the representations in a self-supervised learning manner. 2) Robust Discriminative Learning (RDL) further mines the discrimination from the learned imperfect predictions after warming up. To tackle the noise in the predicted pseudo labels, RDL leverages a novel Robust Concentrating Learning Loss (RCLL) to alleviate the influence of the uncertain samples, thus embracing robustness against noisy pseudo labels. 3) Modality-invariance Learning Mechanism (MLM) minimizes the cross-modal discrepancy to enforce SSM and RDL to produce common representations. We conduct comprehensive experiments on four 2D-3D multimodal datasets, comparing our method against 14 state-of-the-art approaches, thereby demonstrating its effectiveness and superiority.

FMCNet + : Feature-Level Modality Compensation for Visible-Infrared Person Re-Identification.

For visible-infrared person re-identification (VI-ReID), current models that compensate modality-specific information strive to generate missing modality images from existing ones to bridge the cross-modality discrepancies. Despite that, those generated images often suffer from low qualities due to the significant modality gap and include interfering information, e.g., inconsistent colors, thus severely degrading the subsequent VI-ReID performance. Alternatively, we propose a feature-level modality compensation network, i.e., FMCNet+, for VI-ReID in this article as an improved version of our previous work (FMCNet). The core of FMCNet + is to compensate for the missing modality-specific information at the feature level, rather than at the image level, enabling our model to generate more person-related and discriminative modality-specific features for VI-ReID. Concretely, FMCNet+ aims to progressively generate missing modality-specific features by fully exploring the relationships among single-modality features, modality-shared features, and modality-specific features, instead of directly generating them through a generative adversarial way as in the previous FMCNet. To this end, three modules, i.e., single-modality feature decomposition (SFD), modality characteristic dictionary learning (MCDL), and missing modality-specific feature compensation (MMFC), are incorporated in FMCNet+. Experimental results demonstrate the superiority of our proposed FMCNet+ over existing ones, especially for those that compensate for modality-specific information at the image level. Our intriguing findings highlight the necessity of feature-level modality compensation in VI-ReID. Our code and pre-trained models will be released on https://github.com/jssyzsfzy/FMCNet_series.

Dual-Stream Transformer With Distribution Alignment for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification(VI-ReID) aims to match the person images captured by visible and infrared cameras and suffers from severe cross-modality discrepancy and intra-modality variations. Existing approaches mainly use convolution neural network (CNN)-based architectures to extract pedestrian features, which fail to capture the long-range dependencies within an image. In addition, previous works usually attempt to bridge the modality gap by using adversarial learning to generate style-consistent images or designing different feature-level metric learning constraints. However, few works consider the cross-modality disparity from the perspective of assessing overall distance distribution discrepancy. To address these problems, we design a pure Transformer-based Visible-Infrared (TransVI) network with a conventional two-stream structure, which can explicitly capture modality-specific representations and learn multi-modality sharable knowledge. TransVI can efficiently address the lack of global dependency in CNN-based architectures due to the multi-head self-attention modules in the transformer, which allows us to capture the long-range dependencies of pedestrian images. Furthermore, we introduce the Cross-Modality Dissimilarity-based Maximum Mean Discrepancy (CMD-MMD) constraint to handle the cross-modality discrepancy at the distance distribution level. Specifically, CMD-MMD leverages intra-modality distribution separability to guide inter-modality distribution separability learning, aligning pair-wise distance distributions of intra- and inter-modality for within-class and between-class, respectively. In this way, the distance distributions of intra- and inter-modality become more similar, significantly mitigating the cross-modality discrepancy and learning more modality invariant representations. Extensive experimental results on two public VI-ReID datasets confirm that our proposed framework can achieve state-of-the-art performance.

Dynamic Weighted Gradient Reversal Network for Visible-infrared Person Re-identification

Due to intra-modality variations and cross-modality discrepancy, visible-infrared person re-identification (VI Re-ID) is an important and challenging task in intelligent video surveillance. The cross-modality discrepancy is mainly caused by the differences between visible images and infrared images, the inherent essence of which is heterogeneous. To alleviate this discrepancy, we propose a Dynamic Weighted Gradient Reversal Network (DGRNet) to enhance the learning of discriminative common representations by confusing the modality discrimination. In the proposed DGRNet, we design the gradient reversal model guiding adversarial training between identity classifier and modality discriminator to reduce the modality discrepancy of the same person in different modalities. Furthermore, we propose an optimization training method, that is, designing dynamic weight of gradient reversal to achieve optimal adversarial training, and dynamic weight has the ability to dynamically and adaptively evaluate the significance of target loss term, without involving hyper-parameter tuning. Extensive experiments were conducted on two public VI Re-ID datasets, SYSU-MM01 and RegDB. The experimental results show that the proposed DGRNet outperforms state-of-the-art methods and demonstrate the effectiveness of the DGRNet to learn more discriminative common representations for VI Re-ID.

General cross-modality registration framework for visible and infrared UAV target image registration

In all-day-all-weather tasks, well-aligned multi-modality images pairs can provide extensive complementary information for image-guided UAV target detection. However, multi-modality images in real scenarios are often misaligned, and images registration is extremely difficult due to spatial deformation and the difficulty narrowing cross-modality discrepancy. To better overcome the obstacle, in this paper, we construct a General Cross-Modality Registration (GCMR) Framework, which explores generation registration pattern to simplify the cross-modality image registration into a easier mono-modality image registration with an Image Cross-Modality Translation Network (ICMTN) module and a Multi-level Residual Dense Registration Network (MRDRN). Specifically, ICMTN module is used to generate a pseudo infrared image taking a visible image as input and correct the distortion of structural information during the translation of image modalities. Benefiting from the favorable geometry correct ability of the ICMTN, we further employs MRDRN module which can fully extract and exploit the mutual information of misaligned images to better registered Visible and Infrared image in a mono-modality setting. We evaluate five variants of our approach on the public Anti-UAV datasets. The extensive experimental results demonstrate that the proposed architecture achieves state-of-the-art performance.

Identity Feature Disentanglement for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) task aims to retrieve persons from different spectrum cameras (i.e., visible and infrared images). The biggest challenge of VI-ReID is the huge cross-modal discrepancy caused by different imaging mechanisms. Many VI-ReID methods have been proposed by embedding different modal person images into a shared feature space to narrow the cross-modal discrepancy. However, these methods ignore the purification of identity features, which results in identity features containing different modal information and failing to align well. In this article, an identity feature disentanglement method is proposed to disentangle the identity features from identity-irrelevant information, such as pose and modality. Specifically, images of different modalities are first processed to extract shared features that reduce the cross-modal discrepancy preliminarily. Then the extracted feature of each image is disentangled into a latent identity variable and an identity-irrelevant variable. In order to enforce the latent identity variable to contain as much identity information as possible and as little identity-irrelevant information, an ID-discriminative loss and an ID-swapping reconstruction process are additionally designed. Extensive quantitative and qualitative experiments on two popular public VI-ReID datasets, RegDB and SYSU-MM01, demonstrate the efficacy and superiority of the proposed method.

Cross-directional consistency network with adaptive layer normalization for multi-spectral vehicle re-identification and a high-quality benchmark

To tackle the challenge of vehicle re-identification (Re-ID) in complex lighting environments and diverse scenes, multi-spectral sources like visible and infrared information are taken into consideration due to their excellent complementary advantages. However, multi-spectral vehicle Re-ID suffers cross-modality discrepancy caused by heterogeneous properties of different modalities as well as a big challenge of the diverse appearance with different views in each identity. Meanwhile, diverse environmental interference leads to heavy sample distributional discrepancy in each modality. In this work, we propose a novel cross-directional consistency network (CCNet) to simultaneously overcome the discrepancies from both modality and sample aspects. In particular, we design a new cross-directional center loss (Lcdc) to pull the modality centers of each identity close to mitigate cross-modality discrepancy, while the sample centers of each identity close to alleviate the sample discrepancy. Such a strategy can generate discriminative multi-spectral feature representations for vehicle Re-ID. In addition, we design an adaptive layer normalization unit (ALNU) to dynamically adjust individual feature distribution to handle distributional discrepancy of intra-modality features for robust learning. To provide a comprehensive evaluation platform, we create a high-quality RGB-NIR-TIR multi-spectral vehicle Re-ID benchmark (MSVR310), including 310 different vehicles from a broad range of viewpoints, time spans and environmental complexities. Comprehensive experiments on both created and public datasets demonstrate the effectiveness of the proposed approach comparing to the state-of-the-art methods. The dataset and code will be released for free academic usage at https://github.com/superlollipop123/Cross-directional-Center-Network-and-MSVR310.

MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification

Visible-infrared person re-identification (VI-ReID), which aims to search identities across different spectra, is a challenging task due to large cross-modality discrepancy between visible and infrared images. The key to reduce the discrepancy is to filter out identity-irrelevant interference and effectively learn modality-invariant person representations. In this paper, we propose a novel Modality Restitution and Compensation Network (MRCN) to narrow the gap between the two modalities. Specifically, we first reduce the modality discrepancy by using two Instance Normalization (IN) layers. Next, to reduce the influence of IN layers on removing discriminative information and to reduce modality differences, we propose a Modality Restitution Module (MRM) and a Modality Compensation Module (MCM) to respectively distill modality-irrelevant and modality-relevant features from the removed information. Then, the modality-irrelevant features are used to restitute to the normalized visible and infrared features, while the modality-relevant features are used to compensate for the features of the other modality. Furthermore, to better disentangle the modality-relevant features and the modality-irrelevant features, we propose a novel Center-Quadruplet Causal (CQC) loss to encourage the network to effectively learn the modality-relevant features and the modality-irrelevant features. Extensive experiments are conducted to validate the superiority of our method on the challenging SYSU-MM01 and RegDB datasets. More remarkably, our method achieves 95.1% in terms of Rank-1 and 89.2% in terms of mAP on the RegDB dataset.

Cross-modal coherence and incoherence of early infant interactive behavior: links to attachment in infants born very preterm or full-term

ABSTRACT Infants exhibit flexibly organized configurations of facial, vocal, affective, and motor behavior during caregiver-infant interactions that convey convergent messages about their internal states and desires. Prior work documents that greater cross-modal discrepancy at 4 months predicts disorganized attachment. Here, we evaluated whether: very preterm (VPT) or full-term (FT) status predicts cross-modal coherence or incoherence in infants’ behavior with the caregiver at 3 months; and, regardless of prematurity, whether cross-modal interactive coherence or incoherence predicts 12-month attachment. Participants included 155 infants (85 FT; 70 VPT), and their mothers followed from birth to 12 months (corrected age). Infants’ cross-modal coherent and incoherent responses were scored microanalytically from videotaped en-face interactions. Infants’ attachment security was evaluated during Ainsworth’s Strange Situation. Infants born VPT exhibited more incoherent cross-modal responses and insecure attachment than infants born FT. Regardless of prematurity, infants’ coherent and incoherent cross-modal interactive behaviors at 3 months predicted different attachment patterns at 12 months.

Spectrum-irrelevant fine-grained representation for visible–infrared person re-identification

Visible–infrared person re-identification (VI-ReID) is an important and practical task for full-time intelligent surveillance systems. Compared to visible person re-identification, it is more challenging due to the large cross-modal discrepancy. Existing VI-ReID methods suffer from heterogeneous structures and the different spectra of visible and infrared images. In this work, we propose the Spectrum-Insensitive Data Augmentation (SIDA) strategy, which effectively alleviates the disturbance in the visible and infrared spectra and forces the network to learn spectrum-irrelevant features. The network also compares samples with both global and local features. We devise a Feature Relation Reasoning (FRR) module to learn discriminative fine-grained representations according to the graph reasoning principle. Compared to the most commonly used uniform partition, our FRR better adopts to the case of VI-ReID, in which human bodies are difficult to align. Furthermore, we design the dual center loss for learning the global feature in order to maintain the intra-modality relations, while learning the cross-modal similarities. Our method achieves better convergence in training. Extensive experiments demonstrate that our method achieves state-of-the-art performance on two visible–infrared cross-modal Re-ID datasets.

HDA[formula omitted]L: Hierarchical Domain-Augmented Adaptive Learning for sketch-based 3D shape retrieval

The sketch-based 3D shape retrieval has been an active but challenging task for several decades. In this paper, we deeply analyze the challenges and propose a novel Hierarchical Domain-Augmented Adaptive Learning (HDA2L) for sketch-based 3D shape retrieval. The first notable challenge is the vast cross-modality discrepancies between sketches and 3D shapes. To this issue, the existing methods restrict the consistency of the final features by establishing a shared cross-domain loss but ignore the feature extraction process, resulting in a limited effect. We argue that the mutual information of the samples from the same class but different domains can provide an important cue to enhance common features captured in the feature extraction process. Thus, we design an Inter-Domain Augmented Network (Inter-DAN) by employing inter-domain feature correlation learning to capture cross-domain mutual information to learn augmented common global features for both sketches and 3D shapes. Another challenge is that the input sketch is various: it may be particularly abstract and contains only the overall outline of the target model, or it may be too sketchy and only contains some salient local regions of the target model. Though existing methods have demonstrated their capability to capture overall features, they always ignore the learning of local discriminative features and fail to adapt to the various changes of input sketches. To address this issue, we design an Intra-Domain Augmented Network (Intra-DAN) for sketches and 3D shapes, respectively, which learns augmented local discriminative features by adopting cascading cross-layer bilinear pooling operations. In addition, we design a Source-Agnostic Adversarial Network (SAAN) to accomplish the adaptive hierarchical domain features fusion, which forces the network to adaptively focus on more discriminative information from global features and local features and further adapt the diversity of the input sketches. The experiments on three benchmark datasets demonstrate that our method obtains superior retrieval performance than the state-of-the-art sketch-based 3D shape retrieval approaches.

Feature Aggregation via Attention Mechanism for Visible-Thermal Person Re-Identification

Visible-thermal person re-identification (VT-ReID) is an image retrieval task that aims at matching the target pedestrian across the visible and thermal modalities. However, intra-class variations and cross-modality discrepancy degrade the performance of VT-ReID. Recent methods focus on extracting discriminative local features of each modality to alleviate the intra-class variations and cross-modality discrepancy, but these methods ignore semantic relations between the local features of two modalities, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , the spatial relations and channel relations. In this paper, we proposed a feature aggregation module (FAM) to enhance the correlation between local features including spatial dependencies and channel dependencies. Furthermore, FAM implements cross-modality feature aggregation on the enhanced features to reduce the cross-modality discrepancy. Moreover, we also proposed near neighbor cross-modality loss (NNCLoss) to mine feature consistency between modalities by constructing a cross-modality near neighbor set, which facilitates feature alignment between two modalities. Extensive experiments on two datasets demonstrate the superior performance of our approach over the existing state-of-the-arts.

Multi-Scale Fine-Grained Alignments for Image and Sentence Matching

Image and sentence matching is a critical task to bridge the visual and textual discrepancy due to the heterogeneous modalities. Great progress has been made by exploring the coarse-grained relationships between images and sentences or fine-grained relationships between regions and words. However, how to fully excavate and exploit corresponding relations between these two modalities is still challenging. In this work, we propose a novel Multi-scale Fine-grained Alignments Network (MFA), which can effectively explore multi-scale visual-textual correspondences to facilitate bridging cross-modal discrepancy. Specifically, word-scale matching module is firstly utilized to mine the basic but fundamental correspondences between a single word and independent region. Then, we propose a phrase-scale matching module to explore the relations between objects with the constraint of attribute and corresponding region, which can further reserve more associated information. To cope with the complex interactions among multiple phrases and images, we design the relation-scale matching module to capture high-order semantics between two modalities. Moreover, each matching module includes visual aggregation and textual aggregations, which can ensure the bi-directional coupling of multi-scale semantics. Extensive qualitative and quantitative experiments on two challenging datasets including Flickr30 K and MSCOCO, show that the proposed method achieves superior performance compared with the existing methods.

Deep Adversarial Cascaded Hashing for Cross-Modal Vessel Image Retrieval

In recent years, cross-modal remote sensing image retrieval(CMRSIR) has attracted a lot of attention in remote sensing(RS) information processing. It's worth mentioning that land cover scenes, whether unimodal or cross-modal, are the primary research contents of remote sensing image retrieval (RSIR), and there are few studies on vessel images captured by RS satellites, let alone cross-modal retrieval tasks. Vessel images have smaller scale, lower resolution, and less detailed information than land cover images, so it's difficult to retrieve the exact images we want. In this paper, a hashing method called deep adversarial cascaded hashing (DACH) is proposed to address these problems. To extract the subtle and discriminative features contained in RS vessel images accurately, we build a deep cascaded network that fuses multilevel features boosted both in depth and width, and the self-attention mechanism can further enhance the fused features. Combined with hash learning, we also design a weighted quintuplet loss to supervise the transition of discrimination and similarity between different metric spaces, and reduce cross-modal discrepancy at the same time. In addition, we apply the deep adversarial constraint to both feature learning and hash learning, trying to bridge the modality gap and achieve a cross-modal retrieval as precise as unimodal retrieval. Comprehensive experiments on two public bimodal vessel image datasets compared with several excellent cross-modal retrieval methods are conducted to demonstrate the effectiveness of our DACH, and the results show that the proposed method is effective and competitive on cross-modal vessel image retrieval tasks, outperforming state-of-the-art methods.

Exploring modality-shared appearance features and modality-invariant relation features for cross-modality person Re-IDentification

Most existing cross-modality person Re-IDentification works rely on discriminative modality-shared features for reducing cross-modality variations and intra-modality variations. Despite their preliminary success, such modality-shared appearance features cannot capture enough modality-invariant discriminative information due to a massive discrepancy between RGB and IR images. To address this issue, on top of appearance features, we further capture the modality-invariant relations among different person parts (referred to as modality-invariant relation features), which help to identify persons with similar appearances but different body shapes. To this end, a Multi-level Two-streamed Modality-shared Feature Extraction (MTMFE) sub-network is designed, where the modality-shared appearance features and modality-invariant relation features are first extracted in a shared 2D feature space and a shared 3D feature space, respectively. The two features are then fused into the final modality-shared features such that both cross-modality variations and intra-modality variations can be reduced. Besides, a novel cross-modality center alignment loss is proposed to further reduce the cross-modality variations. Experimental results on several benchmark datasets demonstrate that our proposed method exceeds state-of-the-art algorithms by a wide margin.