Xiaoyu Guo

Dr. Xiaoyu Guo


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XGXiaoyu Guo
Xiaoyu Guo
XWXiang Wei
Xiang Wei
SZShunli Zhang
Shunli Zhang
WLWei Lu
Wei Lu
WXWeiwei Xing
Weiwei Xing
Despite the astounding progress made in semi-supervised learning (SSL) and imbalanced supervised learning (ISL), there has been little attention devoted to the research of imbalanced semi-supervised learning (ISSL). The ‘Matthew effect’, a phenomenon where a disparity in data representation becomes more severe in a class-imbalanced dataset during training, could be amplified in a semi-supervised setting. In this study, we addressed two key challenges in ISSL: maintaining the reliability of pseudo-labels and ensuring a balanced representation of features. Specifically, we propose a class-aware feature-diffusion constraint and reliable pseudo-labeling (DCRP) framework to address these issues. In the DCRP, we counteract the overconfidence problem of softmax by adding an extra class to the typical K class problem without the need for additional parameters. Moreover, we introduced a flexible class-aware feature diffusion constraint in the feature extractor, promoting a more balanced feature diversity. Experimental validations on various datasets, such as CIFAR10-LT, CIFAR100-LT, SVHN-LT, and Small ImageNet-127, demonstrated consistent improvements in accuracy with our DCRP method. In particular, we achieved a steady improvement in accuracy of approximately 1% under the newly published ACR prototype across most settings. The code is available at https://github.com/guoxiaoyuatbjtu/DCRP .

30 November 2023 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
XGXiaoyu Guo
Xiaoyu Guo
XKXiangyuan Kong
Xiangyuan Kong
WXWeiwei Xing
Weiwei Xing
XWXiang Wei
Xiang Wei
JZJian Zhang
Jian Zhang
WLWei Lu
Wei Lu

14 October 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
QTQianying Tang
Qianying Tang
XGXiaoyu Guo
Xiaoyu Guo
XWXiang Wei
Xiang Wei
XLXinyu Li
Xinyu Li
DWDongjin Wang
Dongjin Wang
SZShunli Zhang
Shunli Zhang
Underwater images, often affected by light attenuation and particle scattering, pose a challenge for restoration, aggravated by the difficulty in obtaining a substantial amount of annotated data. Existing methods have tackled this issue through the development of semi-supervised frameworks; however, they commonly lack a suitable strategy or rely on additional models trained on extra data to ensure the quality of pseudo-labels. To address this, we propose a self-assessment training framework for semi-supervised underwater image restoration (SAT-UIR). SAT-UIR employs a dual-task network (DT-Net) incorporating an auxiliary assessment task to align the restored image with a target structure similarity index measure score. This enables accurate restoration completeness estimation at a feature level and effective pseudo-label filtering during self-training. Leveraging multi-scale features, the assessment task also encourages the model to learn advantageous features for image restoration. Moreover, we integrate a soft ranking loss to further refine the training process of the auxiliary assessment task. Comprehensive experiments on various underwater benchmarks demonstrate that SAT-UIR outperforms state-of-the-art methods quantitatively and qualitatively. The code is available at https://github.com/aroid721/SAT-UIR.

21 May 2020 in Electronics
Verified
Journal Article
Open access
PDF file
YYYuxiang Yang
Yuxiang Yang
WXWeiwei Xing
Weiwei Xing
SZShunli Zhang
Shunli Zhang
QYQi Yu
Qi Yu
XGXiaoyu Guo
Xiaoyu Guo
MGMin Guo
Min Guo
Visual object tracking by Siamese networks has achieved favorable performance in accuracy and speed. However, the features used in Siamese networks have spatially redundant information, which increases computation and limits the discriminative ability of Siamese networks. Addressing this issue, we present a novel frequency-aware feature (FAF) method for robust visual object tracking in complex scenes. Unlike previous works, which select features from different channels or layers, the proposed method factorizes the feature map into multi-frequency and reduces the low-frequency information that is spatially redundant. By reducing the low-frequency map’s resolution, the computation is saved and the receptive field of the layer is also increased to obtain more discriminative information. To further improve the performance of the FAF, we design an innovative data-independent augmentation for object tracking to improve the discriminative ability of tracker, which enhanced linear representation among training samples by convex combinations of the images and tags. Finally, a joint judgment strategy is proposed to adjust the bounding box result that combines intersection-over-union (IoU) and classification scores to improve tracking accuracy. Extensive experiments on 5 challenging benchmarks demonstrate that our FAF method performs favorably against SOTA tracking methods while running around 45 frames per second.

30 October 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
XGXiaoyu Guo
Xiaoyu Guo
WXWeiwei Xing
Weiwei Xing
JFJun Fang
Jun Fang
JCJia Chen
Jia Chen
XCXi Chen
Xi Chen
Ruipeng GaoRuipeng Gao
Ruipeng Gao
Predicting the estimated time of arrival (ETA) is crucial for ride-hailing platforms and autonomous vehicle systems. Although deep neural network-based models have demonstrated high accuracy in ETA prediction, their loss functions often assume standard noise distribution, which fails to account for the noise distribution in real-world mobile crowdsensing travel orders. This study investigates the dynamic noise distribution in practical travel orders and identifies two key types of noise in ETA prediction: intrinsic noise at the start or end of the order and accumulated noise during travel. To address this issue, we propose a novel method called Noise-aware Optimization (NAO) for ETA prediction that generates dynamic noise distributions from real-world datasets and optimizes the ETA model through maximum likelihood estimation accordingly. We provide two specific forms of NAO for ETA prediction with Gaussian and Laplace noise distributions, respectively, to facilitate practical applications. Additionally, we compare commonly used regression loss functions with NAO under a probability interpretation to illustrate the principle of NAO. Our experiments conducted on the DiDi platform in two large cities demonstrate the superior effectiveness of NAO over other loss functions.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
WXWeiwei Xing
Weiwei Xing
YCYue Cheng
Yue Cheng
HYHongzhu Yi
Hongzhu Yi
XGXiaohui Gao
Xiaohui Gao
XWXiang Wei
Xiang Wei
XPXinyu Pang
Xinyu Pang
Classifiers often learn to be biased corresponding to the class-imbalanced dataset under the semi-supervised learning (SSL) set. While previous work tries to appropriately re-balance the classifiers by subtracting a class-irrelevant image's logit, we further utilize a cheaper form of consistency gradients, which can be widely applicable to various class-imbalanced SSL (CISSL) models. We theoretically analyze that the process of refining pseudo-labels with a baseline image (solid color image without any patterns) in the basic SSL algorithm implicitly utilizes integrated gradient flow training, which can improve the attribution ability. Based on the analysis, we propose a consistently conflicting gradient-based debiasing scheme dubbed LCGC, by encouraging biased class predictions during training. We intentionally update the pseudo-labels whose gradient conflicts with the debiased logits, which is represented as the optimization direction offered by the over-imbalanced classifier predictions. Then, we debias the predictions by subtraction the baseline image logits during testing. Extensive experiments demonstrate that our method can significantly improve the prediction accuracy of existing CISSL models on public benchmarks.