MKSNet: Advanced Small Object Detection in Remote Sensing Imagery with Multi-Kernel and Dual Attention Mechanisms

TL;DR

MKSNet introduces a novel architecture with multi-kernel selection and dual attention mechanisms to improve small object detection in remote sensing images, effectively capturing contextual information and focusing on relevant regions.

Contribution

The paper proposes MKSNet, a new network architecture that adaptively selects kernel sizes and employs dual attention modules to enhance small object detection in remote sensing imagery.

Findings

Outperforms existing models on DOTA-v1.0 and HRSC2016 benchmarks

Significantly improves detection accuracy for small objects

Effectively manages multi-scale and high-resolution image complexities

Abstract

Deep convolutional neural networks (DCNNs) have substantially advanced object detection capabilities, particularly in remote sensing imagery. However, challenges persist, especially in detecting small objects where the high resolution of these images and the small size of target objects often result in a loss of critical information in the deeper layers of conventional CNNs. Additionally, the extensive spatial redundancy and intricate background details typical in remote-sensing images tend to obscure these small targets. To address these challenges, we introduce Multi-Kernel Selection Network (MKSNet), a novel network architecture featuring a novel Multi-Kernel Selection mechanism. The MKS mechanism utilizes large convolutional kernels to effectively capture an extensive range of contextual information. This innovative design allows for adaptive kernel size selection, significantly enhancing the network's ability to dynamically process and emphasize crucial spatial details for small object detection. Furthermore, MKSNet also incorporates a dual attention mechanism, merging spatial and channel attention modules. The spatial attention module adaptively fine-tunes the spatial weights of feature maps, focusing more intensively on relevant regions while mitigating background noise. Simultaneously, the channel attention module optimizes channel information selection, improving feature representation and detection accuracy. Empirical evaluations on the DOTA-v1.0 and HRSC2016 benchmark demonstrate that MKSNet substantially surpasses existing state-of-the-art models in detecting small objects in remote sensing images. These results highlight MKSNet's superior ability to manage the complexities associated with multi-scale and high-resolution image data, confirming its effectiveness and innovation in remote sensing object detection.