Yuxuan Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yuxuan Xiao has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Jian Yang
Nanjing University of Science and Technology, Nanjing, China
3 shared publications - Shanshan Zhang
Nanjing University of Science and Technology
3 shared publications - Aiwen Jiang
School of Artificial Intelligence, Jiang Xi Normal University, NanChang, China
2 shared publications - Changhong Liu
Jiangxi Normal University
2 shared publications - Mingwen Wang
Jiangxi Normal University
2 shared publications
Latest Publications
- 18 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Unleashing the potential of traditional person re-ID methods to clothes changed scenario via curriculum learning
- 18 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Unleashing the potential of traditional person re-ID methods to clothes changed scenario via curriculum learning
- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 181-185
Siamese Feature Decoupling and Adaptive Prototype Alignment for Clothes Changed Person Re-Identification
The core to tackle clothes changed person re-identification is to extract clothes-irrelevant features. Previous methods typically decoupled the entire image features into clothes-relevant and ID-relevant ones via an auxiliary task of clothes classification, yet in this way, it is not guaranteed that the ID-relevant features fully get rid of clothes-relevant information, as the entire image feature also includes other information, such as posture. To enhance the purity of ID-relevant features, this letter proposes a simple yet effective siamese feature decoupling and adaptive prototype alignment framework (Decoupling and Alignment, D${\&}$ A), which involves a reference branch and an alignment branch. Specifically, the reference branch first uses human parsing to remove clothes information at the image level to ensure that the ID prototype subsequently extracted by the image encoder is purely ID-relevant without clothes; the alignment branch excludes clothes information from the ID-relevant features by dual-token decoupling, and then aligns the ID-relevant features with the ID prototypes in the reference branch to enhance the purity of the identity information obtained after decoupling. Furthermore, we introduce an adaptive update strategy to update the ID prototypes to prevent the ID prototypes and the decoupled features from shifting in feature space. Extensive experiments on widely used benchmarks (PRCC, LTCC, and VC-Clothes) validate the effectiveness of our method, which achieves new state-of-the-art results across most metrics.- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 181-185
Siamese Feature Decoupling and Adaptive Prototype Alignment for Clothes Changed Person Re-Identification
The core to tackle clothes changed person re-identification is to extract clothes-irrelevant features. Previous methods typically decoupled the entire image features into clothes-relevant and ID-relevant ones via an auxiliary task of clothes classification, yet in this way, it is not guaranteed that the ID-relevant features fully get rid of clothes-relevant information, as the entire image feature also includes other information, such as posture. To enhance the purity of ID-relevant features, this letter proposes a simple yet effective siamese feature decoupling and adaptive prototype alignment framework (Decoupling and Alignment, D${\&}$ A), which involves a reference branch and an alignment branch. Specifically, the reference branch first uses human parsing to remove clothes information at the image level to ensure that the ID prototype subsequently extracted by the image encoder is purely ID-relevant without clothes; the alignment branch excludes clothes information from the ID-relevant features by dual-token decoupling, and then aligns the ID-relevant features with the ID prototypes in the reference branch to enhance the purity of the identity information obtained after decoupling. Furthermore, we introduce an adaptive update strategy to update the ID prototypes to prevent the ID prototypes and the decoupled features from shifting in feature space. Extensive experiments on widely used benchmarks (PRCC, LTCC, and VC-Clothes) validate the effectiveness of our method, which achieves new state-of-the-art results across most metrics.- 8 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 7 (4) , 770-779
Domain Invariant Noise-Tolerant Learning for Unsupervised Cross-Domain Person Re-ID
In this paper, we focus on tackling the task of unsupervised cross-domain adaptation on person re-identification (UDA re-ID). Most previous methods formulate UDA re-ID as a semi-supervised learning problem and aim to generate pseudo-labels on the target domain for training. However, the quality of pseudo-labels is far from satisfactory due to large domain gaps. To address this problem, in this work, we propose to improve the quality of pseudo-labels by handling domain shifts. Specifically, we narrow down the domain gap via domain style normalization and allow the model to behave more robustly to domain shifts by applying different perturbations on the target data. Furthermore, we point out that noises are inevitable in pseudo-labels and propose a noise-tolerant learning paradigm, which consists of positive learning on latent clean pseudo-labels and negative learning on latent noisy pseudo-labels. We conduct experiments under different adaptation scenarios, including syntheticreal and realreal, and demonstrate that our proposed Domain Invariant Noise-Tolerant Learning (DINTL) method achieves state-of-the-art results without additional parameters.
- 8 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 7 (4) , 770-779
Domain Invariant Noise-Tolerant Learning for Unsupervised Cross-Domain Person Re-ID
In this paper, we focus on tackling the task of unsupervised cross-domain adaptation on person re-identification (UDA re-ID). Most previous methods formulate UDA re-ID as a semi-supervised learning problem and aim to generate pseudo-labels on the target domain for training. However, the quality of pseudo-labels is far from satisfactory due to large domain gaps. To address this problem, in this work, we propose to improve the quality of pseudo-labels by handling domain shifts. Specifically, we narrow down the domain gap via domain style normalization and allow the model to behave more robustly to domain shifts by applying different perturbations on the target data. Furthermore, we point out that noises are inevitable in pseudo-labels and propose a noise-tolerant learning paradigm, which consists of positive learning on latent clean pseudo-labels and negative learning on latent noisy pseudo-labels. We conduct experiments under different adaptation scenarios, including syntheticreal and realreal, and demonstrate that our proposed Domain Invariant Noise-Tolerant Learning (DINTL) method achieves state-of-the-art results without additional parameters.
- 19 September 2021
- Published by Hindawi Limited in International Journal of Intelligent Systems
- Vol. 37 (2) , 1222-1238
Semantic‐aware automatic image colorization via unpaired cycle‐consistent self‐supervised network
Automatic image colorization without manual interventions is an ill-conditioned and inherently ambiguous problem. Most of existing methods focus on formulating colorization as a regression problem and learn parametric mappings from grayscale to color through deep neural networks. Due to the multimodalities of color-grayscale space, in many applications, it is not required to recover exact ground-truth color. Pair-wise pixel-to-pixel learning-based algorithms lack rationality. Techniques such as color space conversion techniques are then proposed to avoid such direct pixel learning. However, the coloring results after color space conversion are blunt and unnatural. In this paper, we hold viewpoints that a reasonable solution is to generate some colorized result that looks natural. No matter what color a region is to be assigned, the colorized region should be semantically and spatially consistent. In this paper, we propose an effective semantic-aware automatic colorization model via unpaired cycle-consistent self-supervised network. Low-level monochrome loss, perceptual identity loss and high-level semantic-consistence loss, together with adversarial loss, are introduced to guide network self-training. We train and test our model on randomly selected subsets from PASCAL VOC 2012. The experimental results including human subjective studies demonstrate that, compared with state-of-the-art methods, our proposed model can achieve more convincing and superior results. Relevant source code is available at https://github.com/YuSuen/ACCycleGAN.
- 19 September 2021
- Published by Hindawi Limited in International Journal of Intelligent Systems
- Vol. 37 (2) , 1222-1238
Semantic‐aware automatic image colorization via unpaired cycle‐consistent self‐supervised network
Automatic image colorization without manual interventions is an ill-conditioned and inherently ambiguous problem. Most of existing methods focus on formulating colorization as a regression problem and learn parametric mappings from grayscale to color through deep neural networks. Due to the multimodalities of color-grayscale space, in many applications, it is not required to recover exact ground-truth color. Pair-wise pixel-to-pixel learning-based algorithms lack rationality. Techniques such as color space conversion techniques are then proposed to avoid such direct pixel learning. However, the coloring results after color space conversion are blunt and unnatural. In this paper, we hold viewpoints that a reasonable solution is to generate some colorized result that looks natural. No matter what color a region is to be assigned, the colorized region should be semantically and spatially consistent. In this paper, we propose an effective semantic-aware automatic colorization model via unpaired cycle-consistent self-supervised network. Low-level monochrome loss, perceptual identity loss and high-level semantic-consistence loss, together with adversarial loss, are introduced to guide network self-training. We train and test our model on randomly selected subsets from PASCAL VOC 2012. The experimental results including human subjective studies demonstrate that, compared with state-of-the-art methods, our proposed model can achieve more convincing and superior results. Relevant source code is available at https://github.com/YuSuen/ACCycleGAN.
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3247-3251
Single Image Colorization Via Modified Cyclegan
In this paper, we focus on automatically colorizing single grayscale image without manual interventions. Most of existing methods tried to accurately restore unknown ground-truth colors and require paired training data for model optimization. However, the ideal restoration objective and strict training constraints limited their performance. Inspired by CycleGAN, we formulate the process of colorization as image-to-image translation and propose an effective color-CycleGAN solution. High-level semantic identity loss and low-level color loss are additionally suggested for model optimization. Our method allows using unpaired images for training and direct prediction in rgb color space, which makes training data collection much easier and more general. We train our model on randomly selected PASCAL VOC 2007 images. All ablation study on loss function and comparisons with state-of-the-art methods are performed on grayscale SUN data. The experiment results show that our improvements on training loss could achieve better content consistence and generate better reasonable colors with less artifacts. Moreover, due to the bidirectional nature of our model, our proposed method provides a by-product that gives an excellent alternative way on color image graying.
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3247-3251
Single Image Colorization Via Modified Cyclegan
In this paper, we focus on automatically colorizing single grayscale image without manual interventions. Most of existing methods tried to accurately restore unknown ground-truth colors and require paired training data for model optimization. However, the ideal restoration objective and strict training constraints limited their performance. Inspired by CycleGAN, we formulate the process of colorization as image-to-image translation and propose an effective color-CycleGAN solution. High-level semantic identity loss and low-level color loss are additionally suggested for model optimization. Our method allows using unpaired images for training and direct prediction in rgb color space, which makes training data collection much easier and more general. We train our model on randomly selected PASCAL VOC 2007 images. All ablation study on loss function and comparisons with state-of-the-art methods are performed on grayscale SUN data. The experiment results show that our improvements on training loss could achieve better content consistence and generate better reasonable colors with less artifacts. Moreover, due to the bidirectional nature of our model, our proposed method provides a by-product that gives an excellent alternative way on color image graying.