LSLinrui Shi

Linrui Shi

*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


Linrui Shi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DuaDiff: Dual-Conditional Diffusion Model for Guided Thermal Image Super-Resolution

    by Linrui Shi, Gaochang Wu, Yingqian Wang, Yebin Liu, Tianyou Chai

    Thermal imaging offers valuable properties, but suffers from inherently low spatial resolution, which can be enhanced using a high-resolution (HR) visible image as guidance. However, the substantial modality differences between thermal and visible images, coupled with significant resolution gaps, pose challenges to existing guided super-resolution (SR) approaches. In this article, we present dual-conditional diffusion (DuaDiff), an innovative diffusion model featuring a dual-conditioning mechanism to enhance guided thermal image SR. Unlike typical conditional diffusion models, DuaDiff integrates a learnable Laplacian pyramid to extract high-frequency details from the visible image, serving as one of the conditioning inputs. By capturing multiscale high-frequency components, DuaDiff effectively focuses on intricate textures and edges in the HR visible images, significantly enhancing thermal image fidelity. Furthermore, we project both thermal and visible images into a semantic latent space, constructing another conditioning input. Leveraging these complementary conditions, DuaDiff employs a multimodal latent feature cross-attention module to facilitate effective interaction between noise, thermal, and visible latent representations. Extensive experiments on the FLIR-ADAS and CATS datasets for $4\times $ and $8\times $ guided SR demonstrate that combining learnable Laplacian conditioning with semantic latent conditioning enables DuaDiff to surpass state-of-the-art methods in both visual quality and metric evaluation, particularly in scenarios with a large resolution gap. Besides, the applications to downstream tasks further confirm the capability of DuaDiff to recover high-fidelity semantic information. The code will be released.


  • Open Access

    Kernel Fisher Dictionary Transfer Learning

    by Linrui Shi, Zheng Zhang, Zizhu Fan, Chao Xi, Zhengming Li, Gaochang Wu

    Dictionary learning is an efficient knowledge representation method that can learn the essential features of data. Traditional dictionary learning methods are difficult to obtain nonlinear information when processing large-scale and high-dimensional datasets. While most dictionary learning algorithms are based on the assumption that the training data and test data have the same feature distribution, which is not always true in practical applications. To address the above problems, we propose the Kernel Fisher Dictionary Transfer Learning (KFDTL) algorithm. First, we map each sample to high-dimensional space through kernel mapping and use any dictionary learning algorithm to learn the essential features. Then, the feature-based transfer learning method is performed to predict the labels of the target samples. This method includes three main contributions: (1) KFDTL constructs a discriminative Fisher embedding model to make the same class samples have similar coding coefficients; (2) Based on the relationship between profiles and atoms, KFDTL constructs an adaptive model that adapts source domain samples to target domain samples; (3) The kernel method is used to efficiently solve nonlinear problems. Experiments on a large number of public image datasets have proved the effectiveness of the proposed method. The source code of the proposed method is available at https://github.com/zzfan3/KFDTL .

  • Real Time Power Equipment Meter Recognition Based on Deep Learning

    by Zizhu Fan, Linrui Shi, Chao Xi, Hui Wang, Song Wang, Gaochang Wu

    Reading power equipment meters often requires loads of manpower, which is a trivial, repetitive, and error-prone task. While conventional automated recognition methods using computer vision (CV) techniques are inflexible under diverse scenarios, in this article, we propose a lightweight meter recognition method that combines deep learning and traditional CV techniques for automated meter reading. For meter detection, an adaptive anchor and global context (GC) module are deployed to improve the feature extraction ability of lightweight backbone without increasing computational cost. Then, an feature pyramid network (FPN) and a path aggregation network (PANet) are developed to realize the information interaction between different feature layers and achieve multiscale prediction. Our method also includes a multitask segmented network to read the detected meters, accelerating the detection speed. Experiments demonstrate that our proposed method can achieve a detection speed of 123 frame per second (FPS) in GeForce GTX 1080 and can obtain an accuracy of 88.2% mean average precision (mAP)50:95. In the case of insufficient training samples, the method can still achieve an accuracy of 80.9% mAP50:95. In addition, we build a power meter images (PMIs) dataset, which contains 1800 images in real scene. The dataset and method we proposed can help with further upgrades of traditional substations. In the future, we also hope to extend the algorithm to edge computing cameras for substations. The newly developed dataset and code are available at https://github.com/zzfan3/electric_meter_detect_recognize .


  • Discriminative Fisher Embedding Dictionary Transfer Learning for Object Recognition

    by Zizhu Fan, Linrui Shi, Qiang Liu, Zhengming Li, Zheng Zhang

    In transfer learning model, the source domain samples and target domain samples usually share the same class labels but have different distributions. In general, the existing transfer learning algorithms ignore the interclass differences and intraclass similarities across domains. To address these problems, this article proposes a transfer learning algorithm based on discriminative Fisher embedding and adaptive maximum mean discrepancy (AMMD) constraints, called discriminative Fisher embedding dictionary transfer learning (DFEDTL). First, combining the label information of source domain and part of target domain, we construct the discriminative Fisher embedding model to preserve the interclass differences and intraclass similarities of training samples in transfer learning. Second, an AMMD model is constructed using atoms and profiles, which can adaptively minimize the distribution differences between source domain and target domain. The proposed method has three advantages: 1) using the Fisher criterion, we construct the discriminative Fisher embedding model between source domain samples and target domain samples, which encourages the samples from the same class to have similar coding coefficients; 2) instead of using the training samples to design the maximum mean discrepancy (MMD), we construct the AMMD model based on the relationship between the dictionary atoms and profiles; thus, the source domain samples can be adaptive to the target domain samples; and 3) the dictionary learning is based on the combination of source and target samples which can avoid the classification error caused by the difference among samples and reduce the tedious and expensive data annotation. A large number of experiments on five public image classification datasets show that the proposed method obtains better classification performance than some state-of-the-art dictionary and transfer learning methods. The code has been available at https://github.com/shilinrui/DFEDTL.