PLPeifu Liu

Peifu 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


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


Latest Publications

  • A Dual-Branch Temporal Deep-Supervised Framework for Remote Sensing Change Detection

    by Jingxuan Xu, Lirong Qiu, Ning Shen, Hao Shen, Peifu Liu, Jianan Li

    In remote sensing applications, change detection serves as a pivotal technology to monitor changes on the land surface by identifying and extracting temporal discrepancies in bitemporal images captured over the same geographical area. Although existing deep learning methods can extract temporal difference features from bitemporal images, these methods often suffer from the attenuation of feature pair distances during long-range encoding and decoding, leading to weakened deep supervision signals. To address this core challenge, this study proposes a pioneering dual-branch temporal deep supervision network, termed DTDNet. The framework employs two independent branches—a front-end semantic branch and a back-end feature mining branch—to achieve multi-dimensional coupling of temporal change features. The former focuses on precise extraction of temporal difference semantics, while the latter is dedicated to effective mining of deep features from bitemporal images. Furthermore, a feature-enhancing Attention Module (FEAM) is innovatively introduced to capture long-range dependencies among token features and learn distance mappings between bitemporal feature pairs, significantly enhancing feature discriminability. Extensive experiments on the MACD, CDD, and SYSU-CD datasets demonstrate that DTDNet achieves breakthrough performance across multiple metrics, substantially advancing the state of the art in change detection technology.

  • Hyperspectral Remote Sensing Images Salient Object Detection: The First Benchmark Dataset and Baseline

    by Peifu Liu, Huiyan Bai, Tingfa Xu, Jihui Wang, Huan Chen, Jianan Li

    The objective of hyperspectral remote sensing image salient object detection (HRSI-SOD) is to identify objects or regions that exhibit distinct spectrum contrasts with the background. This area holds significant promise for practical applications; however, progress has been limited by a notable scarcity of dedicated datasets and methodologies. To bridge this gap and stimulate further research, we introduce the first HRSI-SOD dataset, termed HRSSD, which includes 704 hyperspectral images and 5327 pixel-level annotated salient objects. The HRSSD dataset poses substantial challenges for salient object detection algorithms due to large scale variation, diverse foreground-background relations, and multi-salient objects. Additionally, we propose an innovative and efficient baseline model for HRSISOD, termed the Deep Spectral Saliency Network (DSSN). The core of DSSN is the Cross-level Saliency Assessment Block, which performs pixel-wise attention and evaluates the contributions of multi-scale similarity maps at each spatial location, effectively reducing erroneous responses in cluttered regions and emphasizes salient regions across scales. Additionally, the High-resolution Fusion Module combines bottom-up fusion strategy and learned spatial upsampling to leverage the strengths of multi-scale saliency maps, ensuring accurate localization of small objects. Experiments on the HRSSD dataset robustly validate the superiority of DSSN, underscoring the critical need for specialized datasets and methodologies in this domain. Further evaluations on the HSOD-BIT and HS-SOD datasets demonstrate the generalizability of the proposed method. The dataset and source code are publicly available at https://github.com/laprf/HRSSD.


  • Spectrum-Oriented Point-Supervised Saliency Detector for Hyperspectral Images

    by Peifu Liu, Tingfa Xu, Guokai Shi, Jingxuan Xu, Huan Chen, Jianan Li

    Hyperspectral salient object detection (HSOD) aims to extract targets or regions with significantly different spectra from hyperspectral images. While existing deep learning-based methods can achieve good detection results, they generally necessitate pixel-level annotations, which are notably challenging to acquire for hyperspectral images. To address this issue, we introduce point supervision into HSOD, and incorporate Spectral Saliency, derived from conventional HSOD methods, as a pivotal spectral representation within the framework. This integration leads to the development of a novel Spectrum-oriented Pointsupervised Saliency Detector (SPSD). Specifically, we propose a novel pipeline, specifically designed for HSIs, to generate pseudo-labels, effectively mitigating the performance decline associated with point supervision strategy. Additionally, Spectral Saliency is employed to counteract information loss during model supervision and saliency refinement, thereby maintaining the structural integrity and edge accuracy of the detected objects. Furthermore, we introduce a Spectrum-transformed Spatial Gate to focus more precisely on salient regions while reducing feature redundancy. We have carried out comprehensive experiments on both HSOD-BIT and HS-SOD datasets to validate the efficacy of our proposed method, using mean absolute error (MAE), E-measure, F-measure, Area Under Curve, and Cross Correlation as evaluation metrics. For instance, on the HSOD-BIT dataset, our SPSD achieves a MAE of 0.031 and an F-measure of 0.878. Thorough ablation studies have substantiated the effectiveness of each individual module and provided insights into the model’s working mechanism. Further evaluations on RGB-thermal salient object detection datasets highlight the versatility of our approach.


  • Dual-Stage Hyperspectral Image Classification Model with Spectral Supertoken

    by Peifu Liu, Tingfa Xu, Jie Wang, Huan Chen, Huiyan Bai, Jianan Li


  • Open Access

    Multi-scale Change-Aware Transformer for Remote Sensing Image Change Detection

    by Huan Chen, Tingfa Xu, Zhenxiang Chen, Peifu Liu, Huiyan Bai, Jianan Li

    Change detection identifies differences between images captured at different times. Real-world change detection faces challenges posed by the diverse and intricate nature of change areas, while current datasets and algorithms are often limited to simpler, consistent changes, reducing their effectiveness in practical applications. Existing dual-branch methods process images independently, risking the loss of change information due to insufficient early interaction. In contrast, single-stream approaches, though improving early integration, lack efficacy in capturing complex changes. To address these limitations, we introduce a novel single-stream framework, the Multi-scale Change-Aware Transformer (MCAT), which features the Dynamic Change-Aware Attention module and the Multi-scale Change-Enhanced Aggregator. The Dynamic Change-Aware Attention module, integrating local self-attention and cross-temporal attention, conducts dynamic iteration on images differences, thereby targeting feature extraction of change areas. The Multi-scale Change-Enhanced Aggregator enables the model to adapt to various scales and complex shapes through local change enhancement and multi-scale aggregation strategies. To overcome the limitations of existing datasets regarding the scale diversity and morphological complexity of change areas, we construct the Mining Area Change Detection dataset. The dataset offers a diverse array of change areas that span multiple scales and exhibit complex shapes, providing a robust benchmark for change detection. Extensive experiments demonstrate that our model outperforms existing methods, especially for irregular and multi-scale changes. Codes and dataset are available at https://github.com/chh11/MCAT.


  • Content-Driven Magnitude-Derivative Spectrum Complementary Learning for Hyperspectral Image Classification

    by Huiyan Bai, Tingfa Xu, Huan Chen, Peifu Liu, Jianan Li

    Extracting discriminative information from complex spectral details in hyperspectral image (HSI) for HSI classification is pivotal. While current prevailing methods rely on spectral magnitude features, they could cause confusion in certain classes, resulting in misclassification and decreased accuracy. We find that the derivative spectrum proves more adept at capturing concealed information, thereby offering a distinct advantage in separating these confusion classes. Leveraging the complementarity between spectral magnitude and derivative features, we propose a Content-driven Spectrum Complementary Network based on Magnitude-Derivative Dual Encoder, employing these two features as combined inputs. To fully utilize their complementary information, we raise a Content-adaptive Point-wise Fusion Module, enabling adaptive fusion of dual-encoder features in a point-wise selective manner, contingent upon feature representation. To preserve a rich source of complementary information while extracting more distinguishable features, we introduce a Hybrid Disparity-enhancing Loss that enhances the differential expression of the features from the two branches and increases the inter-class distance. As a result, our method achieves state-of-the-art results on the extensive WHU-OHS dataset and eight other benchmark datasets.


  • DMSSN: Distilled Mixed Spectral–Spatial Network for Hyperspectral Salient Object Detection

    by Haolin Qin, Tingfa Xu, Peifu Liu, Jingxuan Xu, Jianan Li

    Hyperspectral salient object detection (HSOD) has exhibited remarkable promise across various applications, particularly in intricate scenarios where conventional RGB-based approaches fall short. Despite the considerable progress in HSOD method advancements, two critical challenges require immediate attention. Firstly, existing hyperspectral data dimension reduction techniques incur a loss of spectral information, which adversely affects detection accuracy. Secondly, previous methods insufficiently harness the inherent distinctive attributes of hyperspectral images (HSIs) during the feature extraction process. To address these challenges, we propose a novel approach termed the Distilled Mixed Spectral-Spatial Network (DMSSN), comprising a Distilled Spectral Encoding process and a Mixed Spectral-Spatial Transformer (MSST) feature extraction network. The encoding process utilizes knowledge distillation to construct a lightweight autoencoder for dimension reduction, striking a balance between robust encoding capabilities and low computational costs. The MSST extracts spectral-spatial features through multiple attention head groups, collaboratively enhancing its resistance to intricate scenarios. Moreover, we have created a large-scale HSOD dataset, HSOD-BIT, to tackle the issue of data scarcity in this field and meet the fundamental data requirements of deep network training. Extensive experiments demonstrate that our proposed DMSSN achieves state-of-the-art performance on multiple datasets. We will soon make the code and dataset publicly available on https://github.com/anonymous0519/HSOD-BIT.