XGXiaoyu Guo

Xiaoyu Guo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaoyu Guo has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • SAT-UIR: Self-Assessment Training for Semi-Supervised Underwater Image Restoration

    by Qianying Tang, Xiaoyu Guo, Xiang Wei, Xinyu Li, Dongjin Wang, 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.


  • Open Access

    LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing

    by Weiwei Xing, Yue Cheng, Hongzhu Yi, Xiaohui Gao, Xiang Wei, Xiaoyu Guo, Yumin Zhang, 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.


  • Open Access

    LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing

    by Weiwei Xing, Yue Cheng, Hongzhu Yi, Xiaohui Gao, Xiang Wei, Xiaoyu Guo, Yuming Zhang, Xinyu Pang

    Classifiers often learn to be biased corresponding to the class-imbalanced dataset, especially 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, but lacks a firm theoretical basis. We theoretically analyze why exploiting a baseline image can refine pseudo-labels and prove that the black image is the best choice. We also indicated that as the training process deepens, the pseudo-labels before and after refinement become closer. Based on this observation, we propose a debiasing scheme dubbed LCGC, which Learning from Consistency Gradient Conflicting, by encouraging biased class predictions during training. We intentionally update the pseudo-labels whose gradient conflicts with the debiased logits, representing the optimization direction offered by the over-imbalanced classifier predictions. Then, we debiased the predictions by subtracting the baseline image logits during testing. Extensive experiments demonstrate that LCGC can significantly improve the prediction accuracy of existing CISSL models on public benchmarks.

  • M-Mix: Patternwise Missing Mix for filling the missing values in traffic flow data

    by Xiaoyu Guo, Weiwei Xing, Xiang Wei, Weibin Liu, Jian Zhang, Wei Lu

  • DCRP: Class-Aware Feature Diffusion Constraint and Reliable Pseudo-Labeling for Imbalanced Semi-Supervised Learning

    by Xiaoyu Guo, Xiang Wei, Shunli Zhang, Wei Lu, 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 .


  • Adaptive graph generation based on generalized pagerank graph neural network for traffic flow forecasting

    by Xiaoyu Guo, Xiangyuan Kong, Weiwei Xing, Xiang Wei, Jian Zhang, Wei Lu


  • Noise-Aware Optimization for Mobile Crowdsensing-Based Travel Time Estimation

    by Xiaoyu Guo, Weiwei Xing, Jun Fang, Jia Chen, Xi Chen, 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.


  • Open Access

    A Learning Frequency-Aware Feature Siamese Network for Real-Time Visual Tracking

    by Yuxiang Yang, Weiwei Xing, Shunli Zhang, Qi Yu, Xiaoyu 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.