25 March 2024 in IEEE Transactions on Geoscience and Remote Sensing
Tiny object detection in the field of remote sensing has always been a challenging and interesting topic. Despite many researchers have been working on this problem, it has not been well solved due to its complexity. In this paper, we analyze the reasons for the poor performance of deep learning-based object detection methods for tiny objects in remote sensing images. Moreover, we propose a new remote sensing image tiny object detection network based on object reconstruction and multiple receptive field adaptive feature enhancement module (MRFAFEM), called ORFENet. Detailedly, object reconstruction aims to reduce the information loss of tiny objects within deep neural networks, which is only used in the training phase and can be discarded in the inference phase. MRFAFEM is designed to enhance the features for detecting tiny objects by dynamically adjusting the multiple receptive field features. We have conducted several experiments on the AI-TODv2 and LEVIR-Ship datasets, both of which are proposed for tiny object detection in remote sensing images. The experimental results indicate the effectiveness of the proposed method. Specifically, the proposed ORFENet can achieve the AP of 24.8% on the AI-TODv2 dataset and 83.3% AP50 on the LEVIR-Ship dataset. The code will be released at https://github.com/dyl96/ORFENet.
6 May 2025 in IEEE Transactions on Geoscience and Remote Sensing
Detecting tiny objects in remote sensing images has been an intriguing yet challenging topic in the remote sensing image processing. While significant progress has been made in many studies, most existing methods focus on improving the accuracy of tiny object detection without particular consideration for computational complexity, which restricts their applicability in resource-limited condi-tions. Therefore, this paper aims to design a lightweight de-tection algorithm tailored for tiny objects in remote sensing images. First, we investigate the impact of the complexity of different components in deep learning-based object detec-tion models on the accuracy of tiny object detection, includ-ing the backbone and detection head. Then, a dedicated backbone for tiny object detection is proposed, achieving competitive detection accuracy while remaining lightweight. Moreover, we propose a lightweight detection head that in-corporates deformable convolution and optimize the chan-nel dimension. Finally, we combine the above methods to introduce a lightweight network, LTDNet, for tiny object detection in remote sensing images. Benefiting from the dedicated designs for the backbone and detection head spe-cifically for tiny objects, the proposed method can achieve competitive detection accuracy with very low parameters and computational complexity. Extensive experiments are conducted on the AI-TODv2 and LEVIR-Ship datasets, and the results demonstrate the effectiveness of our proposed method. Specifically, the proposed method achieves 54.6% AP50 on the AI-TODv2 dataset with only 4.85M parameters and 38.19G FLOPs. The code will be released soon on the site of https://github.com/dyl96/LTDNet.
7 March 2024 in IEEE Geoscience and Remote Sensing Letters
In the field of remote sensing, the detection of tiny objects has always been an interesting and highly regarded issue. Although many researchers have dedicated their efforts to studying this problem, it still presents numerous challenges due to the complexity of the environment in which tiny objects are presented in remote sensing images. To this end, we propose a remote sensing image tiny objects detection method based on explicit semantic guidance, with a specific focus on regions containing tiny objects. Specifically, we incorporate supervision of the tiny object regions during the training process. This supervision allowed us to extract tiny object regions, thereby forming an explicit attention map. This explicit attention map is employed to semantically modulate the feature map for detecting tiny objects, thus enhancing the regions containing tiny objects while suppressing the background. Extensive experiments are conducted on the AI-TODv2 dataset and the proposed method can achieve an AP of 24.6%. The experimental results demonstrate the effectiveness of the proposed tiny object detection method based on explicit semantic guidance. The code will be released soon on the site of https://github.com/dyl96/ESG_TODNet.
5 October 2025 in Neurocomputing
15 August 2025 in IEEE Transactions on Geoscience and Remote Sensing
In practical applications, varying imaging conditions cause spectral shifts for the same class across hyperspectral image (HSI) domains. Besides, since annotating HSIs is time-consuming, the number of available labeled samples is insufficient, resulting in strong models to overfit during training. To address these issues, a spectral--spatial structure refactoring-based data representation method and a lightweight shift reduction domain generalization network (SRDGnet) are proposed for cross-domain classification. Specifically, a spectral-spatial exchange attribute extraction module (SE-AEM) is designed to capture fine-grained spectral local features, while an integrated feature extraction head (IFEH) is used to extract global features. They both map their respective features into a low-dimensional space. Subsequently, a domain shift reduction module (DSRM) fuses the features for information interaction to reduce domain shift and then feeds them to a lightweight version of the integrated feature extraction module (IFEM)-light for domain-invariant and discriminative features of classes, which are then used for final classification. Moreover, the training leverages multisource domains and a batch-wise traversal constraint strategy to enhance sample diversity and utilization. Experimental results on four public HSI datasets demonstrate that the proposed method can effectively learn a model with higher generalization ability and stability. On the Houston 2013 dataset, it achieves an overall accuracy (OA) of 89.35%, which is 2.67% higher than the best performance of other comparison methods. The code will be released soon on the site of https://github.com/Cherrieqi/SRDGnet
25 February 2026 in IEEE Transactions on Geoscience and Remote Sensing
With the rapid advancement of remote sensing satellites toward higher spatial resolution and revisit frequency, the explosive growth of image data has posed severe challenges to the efficiency of space-to-ground transmission. Traditional onboard compression standards, such as JPEG2000, often fail to maintain satisfactory reconstruction quality under high compression ratios, limiting their applicability in large-scale remote sensing scenarios. Although learned image compression (LIC) methods have achieved remarkable improvements in rate-distortion (RD) performance, their high computational complexity hinders deployment on resource-constrained onboard platforms. To address these challenges, this article proposes remote sensing-lightweight learned image compression (RS-LLIC), a lightweight LIC framework with knowledge distillation (KD) tailored for onboard remote sensing, following the “onboard encoding and ground decoding” paradigm. Specifically, an efficient encoder architecture is designed to significantly reduce onboard computational costs, while a knowledge distillation-based training strategy is introduced to guide the lightweight encoder in feature learning using a teacher model, thereby improving RD performance without incurring additional inference overhead. Experimental results on multiple remote sensing datasets demonstrate that the proposed RS-LLIC achieves superior compression performance with extremely low encoder complexity, providing an effective solution for high-quality and efficient onboard remote sensing image compression. The code will be released on https://github.com/dyl96/RS-LLIC