Lightweight Multi-Scale Feature Extraction with Fully Connected LMF Layer for Salient Object Detection

TL;DR

This paper introduces LMFNet, a lightweight neural network with a novel multi-scale feature extraction layer using depthwise separable dilated convolutions, achieving high accuracy in salient object detection with minimal parameters.

Contribution

The paper presents the LMF layer and LMFNet, a new lightweight architecture that effectively balances efficiency and performance in multi-scale feature extraction for salient object detection.

Findings

Achieves state-of-the-art results on five benchmark datasets.

Uses only 0.81 million parameters, outperforming other lightweight models.

Maintains competitive accuracy while significantly reducing model size.

Abstract

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