MLMengkun Liu

Mengkun 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


Mengkun Liu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    HP-Net: Hierarchical Pooling Interaction Network for RGB-D Salient Object Detection

    by Tao Gao, Weiguang Zhao, Mengkun Liu, Ting Chen, Jing Zhang, Chao Shen, Ziqi Li

    RGB-D saliency object detection emphasizes the integration of RGB and depth map cues to effectively distinguish between foreground and background regions.Most methods concentrate on crafting various cross-modal fusion modules to seamlessly incorporate multi-modal information into features.However, for many real-life cases where the depth maps have poor quality or contain abundant saliency cues, these methods would yield error-proneresults.In this paper, we propose a Hierarchical Pooling Interaction Network (HP-Net) to effectively exploit complementary information for RGB-D salient object detection.To mitigate the impact of low-quality depth maps and facilitate cross-modal fusion, we design a Hierarchical Pooling Interaction Module (HPIM) to adaptively filter useful information from RGB and depth features and to further optimize multi-scale information.Subsequently, we propose a Cross-modal Mutual Attention (CMMA) unit to obtain high-level semantic information, which could roughly locate the salient object positions and offer initial guidance for the decoding process.Moreover, a Bi-directional Gated Module (BGM) based on GRU is utilized to progressively obtain saliency results from coarse to fine in a gated manner.Experimental results and theoretical analysis reveal that the proposed network outperforms existing methods in enhancing detection capabilities across five benchmark datasets.

  • A Lightweight Multifeature Hybrid Mamba for Remote Sensing Image Scene Classification

    by Huihui Dong, Jingcao Li, Zongfang Ma, Zhijie Li, Mengkun Liu, Xiaohui Wei, Licheng Jiao

    Remote sensing (RS) image scene classification has wide applications in the field of RS. Although the existing methods have achieved remarkable performance, there are still limitations in feature extraction and lightweight design. Current multibranch models, although performing well, have large parameter counts and high computational costs, making them difficult to deploy on resource-constrained edge devices, such as uncrewed aerial vehicles (UAVs). On the other hand, lightweight models like StarNet, having less parameter, but rely on elementwise multiplication to generate features and lack the capture of explicit long-range spatial feature, resulting in insufficient classification accuracy. To address these issues, this letter proposes a lightweight mamba-based hybrid network, namely LMHMamba, whose core is an innovative lightweight multifeature hybrid Mamba (LMHM) module. This module combines the advantage of StarNet in implicitly generating high-dimensional nonlinear features, introduces a lightweight state-space module to enhance spatial feature learning capabilities, and then uses local and global attention modules to emphasize local and global features. This enables effective multidimensional feature fusion while maintaining low parameter. We validate the performance of LMHMamba model on three RS scene classification datasets and compare it with mainstream lightweight models and the latest methods. Experimental results show that LMHMamba achieves advanced levels in both classification accuracy and computational efficiency, significantly outperforming the existing lightweight models, providing an efficient solution for edge deployment. Code is available at https://github.com/yizhilanmaodhh/LMHMamba


  • FUNet: Frequency-Aware and Uncertainty-Guiding Network for Rain-Hazy Image Restoration

    by Mengkun Liu, Tao Gao, Yao Liu, Yuhan Cao, Licheng Jiao

    Restoring rain-hazy images is vital for intelligent decision-making in autonomous driving and outdoor surveillance systems, which is a challenging ill-posed problem due to the irreversible nature of image degradation. Despite remarkable success achieved through deep learning, current algorithms are primarily evaluated using given kind of images, and the texture details and frequency domain information are insufficiently explored in most approaches, which greatly limits the performance of the model. To alleviate the above challenges, the frequency-aware and uncertainty-guiding network (FUNet) is proposed for rain-hazy image restoration. The FUNet consists of an end-to-end encoder-decoder architecture with the uncertainty-guided feature refinement (UGFR) and the confidence feature feedback module (CFF). First, the UGFR is designed with the uncertainty estimation (UE), uncertainty local global feature extraction module (ULG), and the frequency component decomposition and fusion (FCDF), which learns the abundant intermediate information in detail for clear image restoration. Second, in order to adequately learn rich semantic features, the CFF module is proposed to provide feedback and guidance on the learning process of the decoder. Third, the frequency-based loss function is designed to ensure training stability, which effectively guarantees the spatial and spectral details of images. Experiments on seven synthetic outdoor datasets and the real-world dataset DQA demonstrate the superiority of the proposed model quantitatively and qualitatively.

  • KCI-Net: Knowledge-Based Contourlet Inference Network for Super-Resolution

    by Mengkun Liu, Licheng Jiao, Xu Liu, Lingling Li, Fang Liu, Shuyuan Yang, Shuang Wang, Biao Hou

    Textural details are useful for image super-resolution, but massive CNN methods ignored the high-frequency components and generated over-smoothed outputs. The knowledge-based contourlet inference network is proposed in this paper. Different from other CNN-based methods that are directly infer high-resolution (HR) images, our model learns to reconstruct the HR image through the series of corresponding contourlet coefficients. Specifically, first, we consider the low-pass subbands of the contourlet as the corresponding low-resolution (LR) image. Then, feed it to the embedding net with residual blocks to provide adequate information for the contourlet coefficients prediction. Finally, we innovatively convert the estimation of contourlet coefficients into the estimation of the generalized gaussian distribution (GGD) parameters, and design the corresponding loss function to ensure training stability, which explores the smoothness of the contour effectively and guarantees the general structure and details of images. Experiments on four remote sensing datasets, four natural scenes and human-made content datasets, and the outdoor dataset demonstrate the superiority of the proposed model quantitatively and qualitatively.


  • Top Cited Papers

    Cross-Level Interaction and Intralevel Fusion Network for Remote Sensing Image Dehazing

    by Yuanbo Wen, Tao Gao, Ting Chen, Ziqi Li, Mengkun Liu, Lidong Liu

    Existing approaches have significantly advanced remote sensing image dehazing. However, they often rely on conventional encoder-decoder architectures, leading to prolonged inference times. To this end, we propose a novel cross-level interaction and intra-level fusion network for remote sensing image dehazing (CINet), which shifts the focus from encoder-decoder dependencies to an innovative hierarchical architecture centered on skip connections, leading to competitive dehazing performance with decreased calculating complexity. Furthermore, we introduce a cross-level multi-view interaction module (CMIM) to facilitate effective interactions between features across hierarchical levels, mitigating the information loss commonly caused by repeated down-sampling operations. Meanwhile, we develop an intra-level dual-dimension fusion module (IDFM), which leverages height-wise and width-wise self-attention to capture rich spatial-aware information, enabling robust and efficient intra-level feature fusion. Additionally, we propose a multi-view progressive extraction block (MPEB), which decomposes features into four distinct components and applies convolutions with diverse kernel sizes, groups, and dilation factors. This design promotes progressive feature learning while significantly reducing computational overhead. Extensive experiments conducted on nine publicly available datasets validate the effectiveness and superiority of our proposed model.


  • Top Cited Papers

    MSNet: Multi-Scale Network for Object Detection in Remote Sensing Images

    by Tao Gao, Shilin Xia, Mengkun Liu, Jing Zhang, Ting Chen, Ziqi Li


  • Open Access

    $C^{2}N^{2}$: Complex-Valued Contourlet Neural Network

    by Mengkun Liu, Licheng Jiao, Xu Liu, Lingling Li, Fang Liu, Shuyuan Yang, Yuwei Guo, Puhua Chen

    Complex-valued convolutional neural networks (CV-CNN) have recently gained recognition in feature representation learning. It implements the repeated application of the operations in convolution, local average pooling, and the absolute value of the resulting vectors. However, it is only conducted in the complex spatial domain, and lacks effective representation of directionality, singularity and regularity in the complex spectral domain for anomaly detection of images. This is the key to feature learning representation of high-order singularity. To solve this problem, a complex-valued contourlet neural network (C $^{2}$ N $^{2}$ ) is proposed in this paper. It is novel in this sense that, different from the CV-CNN in the spatial domain, the spectral stream of C $^{2}$ N $^{2}$ can enhance the multi-resolution sparse representation of nonsubsampled contourlet (NSCT) with multi-scales and multi-directions for images. Furthermore, the spectral feature integration module (SFIM) is proposed to capture the statistical properties of the NSCT coefficients. It is shown that the proposed network can improve the distinguishability of feature learning, and classification ability in theoretical analysis and experiments on three benchmark datasets (Flevoland, Xi'an, and Germany) compared with developed methods. PolSAR image classification is widely used in the fields of agriculture, forestry and military. It must be emphasized that there is potential in effective feature learning representation and the generalization capability of C $^{2}$ N $^{2}$ in deep learning, recognition and interpretation.


  • Multi-Scale Contourlet Knowledge Guide Learning Segmentation

    by Mengkun Liu, Licheng Jiao, Xu Liu, Lingling Li, Fang Liu, Shuyuan Yang, Shuang Wang, Biao Hou

    For accurate segmentation, effective feature extraction has always been a challenging problem, since the variability of appearance and the fuzziness of object boundaries. Convolutional neural networks have recently gained recognition in feature representation learning. However, it is only conducted in the spatial domain, and lacks effective representation of directionality, singularity and regularity in the spectral domain for anomaly detection of images. This is the key to feature learning representation of high-order singularity. To solve this problem, a multi-scale contourlet knowledge guide learning network is proposed in this paper. It is novel in this sense that, different from the CNNs in the spatial domain, the proposed method learns the multi-scale contourlet sparse representation to obtain more effective and sparse features in multi-scales and multi-directions. Furthermore, the contourlet knowledge guide learning can enhance the representation of spectral domain features. It is shown that the proposed network can learn the multi-level discriminative features and capture the more accurate object boundaries. The segmentation ability in theoretical analysis and experiments on five polyp segmentation datasets (CVC-ColonDB, CVC-ClinicDB, Kvasir-SEG, ETIS-LaribPolypDB, EndoSceneStill) and two building datasets (Massachusetts, WHU) are compared with developed methods. It must be emphasized that there is potential in effective feature learning representation and the generalization capability of the proposed method in deep learning, recognition and interpretation.