SDCoNet: Saliency-Driven Multi-Task Collaborative Network for Remote Sensing Object Detection

2026-01-18

AI Summary

This work addresses the challenges of detecting small objects in low-quality remote sensing imagery, where complex backgrounds, weak signals, and limited spatial resolution hinder performance. Existing approaches that sequentially apply super-resolution followed by detection suffer from misaligned optimization objectives and redundant feature representations. To overcome these limitations, the authors propose SDCoNet, a unified framework that implicitly couples super-resolution and detection through a shared Swin Transformer encoder. A multi-scale saliency prediction module is introduced to emphasize weak target regions while suppressing background clutter, and a gradient routing strategy is designed to alleviate optimization conflicts in multi-task learning. Extensive experiments on benchmark datasets—including NWPU VHR-10-Split, DOTAv1.5-Split, and HRSSD-Split—demonstrate that SDCoNet significantly outperforms state-of-the-art methods, achieving substantial gains in small object detection accuracy without compromising computational efficiency.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

In remote sensing images, complex backgrounds, weak object signals, and small object scales make accurate detection particularly challenging, especially under low-quality imaging conditions. A common strategy is to integrate single-image super-resolution (SR) before detection; however, such serial pipelines often suffer from misaligned optimization objectives, feature redundancy, and a lack of effective interaction between SR and detection. To address these issues, we propose a Saliency-Driven multi-task Collaborative Network (SDCoNet) that couples SR and detection through implicit feature sharing while preserving task specificity. SDCoNet employs the swin transformer-based shared encoder, where hierarchical window-shifted self-attention supports cross-task feature collaboration and adaptively balances the trade-off between texture refinement and semantic representation. In addition, a multi-scale saliency prediction module produces importance scores to select key tokens, enabling focused attention on weak object regions, suppression of background clutter, and suppression of adverse features introduced by multi-task coupling. Furthermore, a gradient routing strategy is introduced to mitigate optimization conflicts. It first stabilizes detection semantics and subsequently routes SR gradients along a detection-oriented direction, enabling the framework to guide the SR branch to generate high-frequency details that are explicitly beneficial for detection. Experiments on public datasets, including NWPU VHR-10-Split, DOTAv1.5-Split, and HRSSD-Split, demonstrate that the proposed method, while maintaining competitive computational efficiency, significantly outperforms existing mainstream algorithms in small object detection on low-quality remote sensing images. Our code is available at https://github.com/qiruo-ya/SDCoNet.

Problem

• remote sensing object detection
• small object detection
• low-quality imaging
• multi-task learning
• super-resolution

Innovation

• Saliency-driven
• Multi-task collaborative learning
• Swin Transformer
• Gradient routing
• Remote sensing object detection