SLShubo Liu

Shubo Liu

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

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


Shubo Liu has a total of 73 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PLZW: FPGA-based Pipelined LZW for lossless compression of edge data

    by Xiao Liu, Akram Y. Sarhan, Shubo Liu, Zhaohui Cai, Guoqing Tu, Faisal S. Alsubaei, Yousef S. Alsahafi

    The rapid growth of IoT devices and data in edge computing applications has created a pressing need for efficient lossless compression of end-edge data. The Lempel-Ziv-Welch (LZW) algorithm, widely used in these scenarios, faces bottlenecks in compression speed due to its inherent data dependency. Unlike existing multi-cycle architectures, we propose PLZW, a pipeline-based LZW acceleration architecture with three novel mechanisms: a data bypass mechanism that allows data to pass directly between pipeline stages, minimizing stalls; a multi-level caching mechanism to reduce pipeline stalls caused by long dictionary update times; and a hash prediction mechanism to improve dictionary lookup hit rates and reduce stall frequency. Our field-programmable gate array (FPGA) implementation demonstrates a 2.5 $$\times $$ × speedup over existing state-of-the-art methods while maintaining competitive power consumption, resource utilization, and compression ratio. Furthermore, the resource utilization remains below 1% of total FPGA resources, and the proposed mechanisms improve the dictionary first-hit rate by 35.8%. This work offers a high-speed, lightweight, generic solution for lossless compression of end-edge data. PLZW provides a reference implementation for optimizing hardware-based data compression in real-time and resource-constrained applications.


  • Open Access

    Revisiting Interpolation for Noisy Label Correction

    by Yuanzhuo Xu, Xiaoguang Niu, Jie Yang, Ruiyi Su, Jian Zhang, Shubo Liu, Steve Drew

    Label correction methods are popular for their simple architecture in learning with noisy labels. However, they suffer severely from false label correction and achieve subpar performance compared with state-of-the-art methods. In this paper, we revisit the label correction methods through theoretical analysis of gradient scaling and demonstrate that the sample-wise dynamic and class-wise uniformity of interpolation weight prevents memorization of the mislabeled samples. We then propose DULC, a simple yet effective label correction method that uses the normalized Jensen-Shannon divergence (JSD) metric as the interpolation weight to promote sample-wise dynamic and class-wise uniformity. Additionally, we provide theoretical evidence that sharpening predictions in label correction facilitates the memorization of true class, and we achieve it by employing the augmentation strategy along with the sharpening function. Extensive experiments on CIFAR-10, CIFAR-100, TinyImageNet, WebVision and Clothing1M datasets demonstrate substantial improvements over state-of-the-art methods.


  • Continuous Latent Adversarial Autoencoder: A Time-Sensitive Method for Incomplete Time-Series Modeling

    by Zhuoqing Chang, Shubo Liu, Zhaohui Cai, Guoqing Tu

    Incomplete time-series modeling is an unavoidable topic in real-world time-series analysis because of the frequent occurrence of missing values in practical data. However, integrating data preprocessing and subsequent analysis within a model can amplify the errors from processed values. Moreover, most existing methods that directly model incomplete time series often fail to infer values at any desired time or support multistep prediction. To address these issues, this article introduces a novel generative model called the continuous latent adversarial autoencoder (CLAAE) for directly modeling incomplete time series. CLAAE can effectively impute missing data of any time point and support multistep prediction. Specifically, CLAAE devises a time-aware long short-term memory (LSTM) encoder to extract temporal and sequential characteristics. The decoder is built upon the augmented neural ordinary differential equation (ANODE), allowing it to infer the probability of missing data across an arbitrary continuous-time horizon. To guarantee the meaningfulness of samples generated from any region within the prior space, a fully connected neural network is utilized as a discriminator, encouraging the aggregated posterior learned by the encoder to be indistinguishable from a selected prior distribution. Extensive experimental results across simulations and real-world datasets demonstrate that CLAAE outperforms baseline methods, especially when the amount of missing data is overwhelming. By combining the autoencoder and adversarial training, CLAAE can significantly enhance the quality of the synthetic samples, respecting the original feature distributions and the temporal dynamics.


  • Top Cited Papers
    Open Access

    AerialVLN: Vision-and-Language Navigation for UAVs

    by Shubo Liu, Hongsheng Zhang, Yuankai Qi, Peng Wang, Yanning Zhang, Qi Wu

    Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap and facilitate research in this field, we propose a new task named AerialVLN, which is UAV-based and towards outdoor environments. We develop a 3D simulator rendered by near-realistic pictures of 25 city-level scenarios. Our simulator supports continuous navigation, environment extension and configuration. We also proposed an extended baseline model based on the widely-used cross-modal-alignment (CMA) navigation methods. We find that there is still a significant gap between the baseline model and human performance, which suggests AerialVLN is a new challenging task. Dataset and code is available at https://github.com/AirVLN/AirVLN.


  • An Improved Sequence-to-Point Learning for Non-Intrusive Load Monitoring Based on Discrete Wavelet Transform

    by Chang Xiong, Zhaohui Cai, Shubo Liu, Jie Luo, Guoqing Tu

    Nonintrusive load monitoring (NILM) is a process that monitors the aggregated power consumption data of customers measured by a single sensor and decomposes the real-time power consumption of each dedicated device. Recent research has been focused on in-depth learning. However, the expensive cost of training time and the huge model scale are not conducive to the realization of smart meters. It is still challenging to accurately predict the real-time power of high-frequency appliances. This paper uses the discrete wavelet transform (DWT) to preprocess the data, which divides the frequency of the training power data. The processed data will be transferred to the enhanced sequence-to-point network (en-S2P) for training. The en-S2P network is the promotion of a sequence-to-point model (S2P) optimized by the autoencoder and bidirectional long short-term memory (Bi-LSTM) layer. And it is compressed by a combined pruning algorithm after being trained. The proposed model method is tested on the UK-DALE and REDD datasets using db2 and sym5 wavelet transform and compared with the S2P. Extensive experiments show that the proposed model can obtain a more satisfactory decomposition performance of appliances, especially high-frequency. In addition, it has a more lightweight scale and maintains a certain degree of sparsity, which is friendly to electricity meters.


  • Open Access

    Audio Anti-Spoofing Based on Audio Feature Fusion

    by Jiachen Zhang, Guoqing Tu, Shubo Liu, Zhaohui Cai

    The rapid development of speech synthesis technology has significantly improved the naturalness and human-likeness of synthetic speech. As the technical barriers for speech synthesis are rapidly lowering, the number of illegal activities such as fraud and extortion is increasing, posing a significant threat to authentication systems, such as automatic speaker verification. This paper proposes an end-to-end speech synthesis detection model based on audio feature fusion in response to the constantly evolving synthesis techniques and to improve the accuracy of detecting synthetic speech. The model uses a pre-trained wav2vec2 model to extract features from raw waveforms and utilizes an audio feature fusion module for back-end classification. The audio feature fusion module aims to improve the model accuracy by adequately utilizing the audio features extracted from the front end and fusing the information from timeframes and feature dimensions. Data augmentation techniques are also used to enhance the performance generalization of the model. The model is trained on the training and development sets of the logical access (LA) dataset of the ASVspoof 2019 Challenge, an international standard, and is tested on the logical access (LA) and deep-fake (DF) evaluation datasets of the ASVspoof 2021 Challenge. The equal error rate (EER) on ASVspoof 2021 LA and ASVspoof 2021 DF are 1.18% and 2.62%, respectively, achieving the best results on the DF dataset.