Lightweight Multi-Scale Feature Extraction with Fully Connected LMF Layer for Salient Object Detection
This addresses the efficiency-performance trade-off in lightweight networks for computer vision tasks like salient object detection, with potential broader applications in image processing.
The paper tackles the challenge of multi-scale feature extraction in lightweight networks for salient object detection by proposing LMFNet, which uses a novel LMF layer with depthwise separable dilated convolutions. It achieves state-of-the-art or comparable results on five benchmark datasets with only 0.81M parameters, reducing parameters while maintaining competitive performance.
In the domain of computer vision, multi-scale feature extraction is vital for tasks such as salient object detection. However, achieving this capability in lightweight networks remains challenging due to the trade-off between efficiency and performance. This paper proposes a novel lightweight multi-scale feature extraction layer, termed the LMF layer, which employs depthwise separable dilated convolutions in a fully connected structure. By integrating multiple LMF layers, we develop LMFNet, a lightweight network tailored for salient object detection. Our approach significantly reduces the number of parameters while maintaining competitive performance. Here, we show that LMFNet achieves state-of-the-art or comparable results on five benchmark datasets with only 0.81M parameters, outperforming several traditional and lightweight models in terms of both efficiency and accuracy. Our work not only addresses the challenge of multi-scale learning in lightweight networks but also demonstrates the potential for broader applications in image processing tasks. The related code files are available at https://github.com/Shi-Yun-peng/LMFNet