Despite salient object detection in natural images (NSI-SOD) has made remarkable progress, it is still an emerging and challenging problem to detect salient objects from optical remote sensing images (RSI-SOD). To improve RSI-SOD based on fully convolutional neural networks (FCNs), attention and edge awareness have been used separately to aid integration and refinement of multi-level features for effective decoding. Although they have been shown to semantically enhance salient features and reduce fuzzy boundaries, the correlation between the semantic-enhanced salient features and edge features is rarely explored, which has inspired the development of a new model to enable close interaction between semantic and edges for fully activating the advantages of attention and edge awareness, and led to the Semantic-Edge Interactive Network (SEINet) presented in this paper. The proposed model consists of two interacting decoding branches based on U-shaped network to achieve SOD and salient edge detection (SED), and the Multi-scale Attention Interaction (MAI) module is proposed to provide edge-enhanced semantic for SOD and semantic-enhanced edge for SED interactively between the two branches. Moreover, to alleviate the problem of semantic dilution, the Semantic-guided Fusion (SF) module is proposed and deployed at the end of the SOD branch. From extensive quantitative and qualitative comparison of the proposed model against the FCN-based models with and without incorporation of attention and edge awareness, the proposed model obtains the most stable scores at different thresholds of the F-measure curve and outperforms 18 state-of-the-art methods. Code has been made available at: https://github.com/LiangBoCheng/SEINet

In recent years, object detection algorithm based on deep learning has made great progress, but the detection effect is not ideal for small objects detection. Some methods use high-resolution features or enhance shallow features to improve the detection accuracy of small objects. However, using high-resolution features for detection needs higher computational cost, and enhancing shallow features by propagating semantic information from high-level into low-level may bring information aliasing. To address this issue, we propose a novel object detection method based on shallow feature fusion and semantic information enhancement (FFSI). The high-level semantic information is injected into low-level features to guide the enhancement of specific detail information. In order to reduce the information aliasing in shallow features and enhance the receptive field of shallow features, we design two parallel modules: context information enhancement module (CIE) and receptive field enhancement module (RFE). CIE highlights the location of objects by establishing the relationship between local and global context information. RFE enhances the receptive field of shallow features by using dilated convolution to adapt to object detection of different scales, especially small objects. The proposed model is evaluated extensively on PASCAL VOC, and COCO datasets. The experimental results demonstrate that the proposed FFSI model has competitive performance. More importantly, this study reveals that FFSI outperforms the state-of-the-art methods in detecting small objects.

Salient Object Detection in Optical Remote Sensing Images (ORSI-SOD) presents distinct challenges, primarily due to the small scale and background similarity of salient objects in images captured by satellite and aerial sensors. Traditional approaches often fail to effectively utilize high-resolution details from shallow features, focusing instead on the semantic depth of features, and typically employ complex, resource-intensive architectures. To overcome these limitations, this paper introduces a novel lightweight network, the Spatial Attention Feedback Iteration Network (SAFINet). SAFINet employs a unique approach by integrating a Feature Refinement via Attention Feedback (FRAF) module and a Spatial Correlation (SCorr) module. The FRAF module refines low-resolution spatial attention using highresolution spatial attention, while the SCorr module enhances the fusion of the spatial attentions. These modules work collaboratively to effectively preserve detail integrity and clarity. Additionally, a Multi-scale Attention Fusion (MAF) module leverages multi-scale information to enrich contextual detail. Our extensive testing on two benchmark datasets shows that SAFINet achieves superior performance in six out of eight metrics, with only 3.12M parameters and 7.63G FLOPs, demonstrating significant improvements over 18 state-of-the-art models. The code and results are available at https://github.com/WangJianQin7/SAFINet .

Salient object detection in optical remote sensing images (ORSIs) is challenging due to small object sizes, low contrast, and complex backgrounds. Existing methods often rely on computationally intensive architectures, limiting their efficiency in real-world applications. To address this, we propose LiteSalNet, a lightweight deep learning framework for ORSI salient object detection. LiteSalNet employs MobileNetV2 as a compact encoder and enhances multiscale feature representation through three modules: the Adaptive Spatial Attention Module (ASAM) for spatial attention refinement, the Dual-Scale Feature Enhancement Module (DSFEM) for local-global feature integration, and the Semantic Context Enhancement Module (SCEM) for high-level semantic refinement. Additionally, a Multi-Stream Progressively Decoding Framework (MSPDF) is introduced to decode saliency, edge, and skeleton maps in a supervised manner, improving boundary precision, suppressing background noise, and enhancing internal object consistency. Extensive experiments on two benchmark ORSI datasets demonstrate that LiteSalNet outperforms 19 state-of-the-art models across multiple evaluation metrics, including F-measure, S-measure, E-measure, and Mean Absolute Error (MAE). Notably, LiteSalNet achieves these results with only 3.90M parameters and 7.35 GFLOPs, ensuring high computational efficiency. The code and results are available at https://github.com/ai-kunkun/LiteSalNet.