The primary goal of visible-infrared person re-identification(VI-ReID)is to match pedestrian photos obtained during the day and night.The majority of existing methods simply generate auxiliary modalities to reduce the...The primary goal of visible-infrared person re-identification(VI-ReID)is to match pedestrian photos obtained during the day and night.The majority of existing methods simply generate auxiliary modalities to reduce the modality discrepancy for cross-modality matching.They capture modality-invariant representations but ignore the extraction of modality-specific representations that can aid in distinguishing among various identities of the same modality.To alleviate these issues,this work provides a novel specific and shared representations learning(SSRL)model for VI-ReID to learn modality-specific and modality-shared representations.We design a shared branch in SSRL to bridge the image-level gap and learn modality-shared representations,while a specific branch retains the discriminative information of visible images to learn modality-specific representations.In addition,we propose intra-class aggregation and inter-class separation learning strategies to optimize the distribution of feature embeddings at afine-grained level.Extensive experimental results on two challenging benchmark datasets,SYSU-MM01 and RegDB,demonstrate the superior performance of SSRL over state-of-the-art methods.展开更多
The goal of the present study was to investigate age-related changes in attentional allocation for shared task representations during joint performance;event-related potentials were recorded while participants perform...The goal of the present study was to investigate age-related changes in attentional allocation for shared task representations during joint performance;event-related potentials were recorded while participants performed a modified visual three-stimulus oddball task, both alone and together with another participant. Younger adults and older adults (14 each) participated in the study. Participants were required to identify rare target stimuli while ignoring frequent standards, as well as rare non-targets assigned to a partner’s action (<i>i.e</i>., no-go stimuli for one’s own task). ERP component, nogo-P3 and P3b were measured to investigate the inhibition and the attentional allocation to the partner’s stimuli. Results showed that younger adults elicited larger frontal nogo P3 and parietal P3b for non-targets in the joint than in the individual condition. Contrary to expectation, older adults induced frontal no-go P3 in the joint condition not in the individual condition. In the sharing of the task with another, the result suggested that the efficiency of matching of incoming information with the representation of the other’s task declined with age, whereas aging did not affect the suppression of incorrect preparation of motor responses instigated by this representation.</i.i.e.<>展开更多
1 Introduction Unsupervised Federated Continual Learning(UFCL)is a new learning paradigm that embeds unsupervised representation techniques into the Federated Learning(FL)framework,which enables continuous training of...1 Introduction Unsupervised Federated Continual Learning(UFCL)is a new learning paradigm that embeds unsupervised representation techniques into the Federated Learning(FL)framework,which enables continuous training of a shared representation model without compromising individual participants’data privacy[1,2].However,the continuous learning process may cause catastrophic forgetting in the model,reducing generated representations’performance.展开更多
The pansharpening process is for obtaining an enhanced image with both high spatial and high spectral resolutions by fusing a panchromatic（PAN） image and a low spatial resolution multispectral（MS） image. Sparse Pr...The pansharpening process is for obtaining an enhanced image with both high spatial and high spectral resolutions by fusing a panchromatic（PAN） image and a low spatial resolution multispectral（MS） image. Sparse Principal Component Analysis（SPCA） method has been proposed as a pansharpening method, which utilizes sparse coefficients and over-complete dictionaries to represent the remote sensing data. However, this method still has some drawbacks, such as the existence of the block effect. In this paper, based on SPCA, we propose the Sparse over Shared Coefficients（SSC）, in which patches are extracted with a sliding distance of 1 pixel from a PAN image, and the MS image shares the sparse representation coefficients trained from the PAN image independently.The fused high-resolution MS image is reconstructed by K-SVD algorithm and iterations, and residual compensation is applied when the down-sampling constraint is not satisfied. The simulated experiment results demonstrate that the proposed SSC method outperforms SPCA and improves the overall effectiveness.展开更多
Multimodal medical imaging of human pathological tissues provides comprehensive information to assist in clinical diagnosis.However,due to the high cost of imaging,physiological incompatibility,and the harmfulness of ...Multimodal medical imaging of human pathological tissues provides comprehensive information to assist in clinical diagnosis.However,due to the high cost of imaging,physiological incompatibility,and the harmfulness of radioactive tracers,multimodal medical image data remains scarce.Currently,cross-modal medical synthesis methods can generate desired modal images from existing modal images.However,most existing methods are limited to specific domains.This paper proposes an Adaptive Domain Medical Image Synthesis Method based on Generative Adversarial Networks(ADGAN)to address this issue.ADGAN achieves multidirectional medical image synthesis and ensures pathological consistency by constructing a single generator to learn the latent shared representation of multiple domains.The generator employs dense connections in shallow layers to preserve edge details and incorporates auxiliary information in deep layers to retain pathological features.Additionally,spectral normalization is introduced into the discriminator to control discriminative performance and indirectly enhance the image synthesis ability of the generator.Theoretically,it can be proved that the proposed method can be trained quickly,and spectral normalization contributes to adaptive and multidirectional synthesis.In practice,comparing with recent state-of-the-art methods,ADGAN achieves average increments of 4.7%SSIM,6.7%MSIM,7.3%PSNR,and 9.2%VIF.展开更多
基金supported by the National Key R&D Program of China(2022ZD0160605)the National Natural Science Foundation of China(61976002)+3 种基金the University Synergy Innovation Program of Anhui Province(GXXT-2022-036)the Natural Science Foundation of Anhui Province(No.2208085J18)the National Natural Science Foundation of China under Grant(62106006)the Natural Science Foundation of Anhui Higher Education Institution(No.2022AH040014).
文摘The primary goal of visible-infrared person re-identification(VI-ReID)is to match pedestrian photos obtained during the day and night.The majority of existing methods simply generate auxiliary modalities to reduce the modality discrepancy for cross-modality matching.They capture modality-invariant representations but ignore the extraction of modality-specific representations that can aid in distinguishing among various identities of the same modality.To alleviate these issues,this work provides a novel specific and shared representations learning(SSRL)model for VI-ReID to learn modality-specific and modality-shared representations.We design a shared branch in SSRL to bridge the image-level gap and learn modality-shared representations,while a specific branch retains the discriminative information of visible images to learn modality-specific representations.In addition,we propose intra-class aggregation and inter-class separation learning strategies to optimize the distribution of feature embeddings at afine-grained level.Extensive experimental results on two challenging benchmark datasets,SYSU-MM01 and RegDB,demonstrate the superior performance of SSRL over state-of-the-art methods.
文摘The goal of the present study was to investigate age-related changes in attentional allocation for shared task representations during joint performance;event-related potentials were recorded while participants performed a modified visual three-stimulus oddball task, both alone and together with another participant. Younger adults and older adults (14 each) participated in the study. Participants were required to identify rare target stimuli while ignoring frequent standards, as well as rare non-targets assigned to a partner’s action (<i>i.e</i>., no-go stimuli for one’s own task). ERP component, nogo-P3 and P3b were measured to investigate the inhibition and the attentional allocation to the partner’s stimuli. Results showed that younger adults elicited larger frontal nogo P3 and parietal P3b for non-targets in the joint than in the individual condition. Contrary to expectation, older adults induced frontal no-go P3 in the joint condition not in the individual condition. In the sharing of the task with another, the result suggested that the efficiency of matching of incoming information with the representation of the other’s task declined with age, whereas aging did not affect the suppression of incorrect preparation of motor responses instigated by this representation.</i.i.e.<>
基金supported by the National Science and Technology Major Project(2022ZD0120203).
文摘1 Introduction Unsupervised Federated Continual Learning(UFCL)is a new learning paradigm that embeds unsupervised representation techniques into the Federated Learning(FL)framework,which enables continuous training of a shared representation model without compromising individual participants’data privacy[1,2].However,the continuous learning process may cause catastrophic forgetting in the model,reducing generated representations’performance.
文摘The pansharpening process is for obtaining an enhanced image with both high spatial and high spectral resolutions by fusing a panchromatic（PAN） image and a low spatial resolution multispectral（MS） image. Sparse Principal Component Analysis（SPCA） method has been proposed as a pansharpening method, which utilizes sparse coefficients and over-complete dictionaries to represent the remote sensing data. However, this method still has some drawbacks, such as the existence of the block effect. In this paper, based on SPCA, we propose the Sparse over Shared Coefficients（SSC）, in which patches are extracted with a sliding distance of 1 pixel from a PAN image, and the MS image shares the sparse representation coefficients trained from the PAN image independently.The fused high-resolution MS image is reconstructed by K-SVD algorithm and iterations, and residual compensation is applied when the down-sampling constraint is not satisfied. The simulated experiment results demonstrate that the proposed SSC method outperforms SPCA and improves the overall effectiveness.
基金supported by the National Natural Science Foundation of China(Nos.62176217 and 62206224)the Innovation Team Funds of China West Normal University(No.KCXTD2022-3)+2 种基金the Postdoctoral Science Foundation of China(No.2023M732428)the Natural Science Foundation of Sichuan Province(No.2022NSFSC0866)the Doctoral Research Innovation Project(No.21E025).
文摘Multimodal medical imaging of human pathological tissues provides comprehensive information to assist in clinical diagnosis.However,due to the high cost of imaging,physiological incompatibility,and the harmfulness of radioactive tracers,multimodal medical image data remains scarce.Currently,cross-modal medical synthesis methods can generate desired modal images from existing modal images.However,most existing methods are limited to specific domains.This paper proposes an Adaptive Domain Medical Image Synthesis Method based on Generative Adversarial Networks(ADGAN)to address this issue.ADGAN achieves multidirectional medical image synthesis and ensures pathological consistency by constructing a single generator to learn the latent shared representation of multiple domains.The generator employs dense connections in shallow layers to preserve edge details and incorporates auxiliary information in deep layers to retain pathological features.Additionally,spectral normalization is introduced into the discriminator to control discriminative performance and indirectly enhance the image synthesis ability of the generator.Theoretically,it can be proved that the proposed method can be trained quickly,and spectral normalization contributes to adaptive and multidirectional synthesis.In practice,comparing with recent state-of-the-art methods,ADGAN achieves average increments of 4.7%SSIM,6.7%MSIM,7.3%PSNR,and 9.2%VIF.
