Lightweight Multi-Scale Feature Extraction with Fully Connected LMF Layer for Salient Object Detection
Not on the map. Why?
Abstract (arXiv)
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
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 10 Aug 2025.
Builds on
27 of 50 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
- 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
- 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
- 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 412
15 more
- 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
- 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
- 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
- 2014The Secrets of Salient Object Segmentationcited by 200
- 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
- 2020Suppress and Balance: A Simple Gated Network for Salient Object Detectioncited by 126
- 2018Reverse Attention for Salient Object Detectioncited by 113
- 2017Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detectioncited by 93
- 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89
- 2020Highly Efficient Salient Object Detection with 100K Parameterscited by 79
- 2017Learning Uncertain Convolutional Features for Accurate Saliency Detectioncited by 44
- 2016Understanding Convolutional Neural Networks with A Mathematical Modelcited by 33
- 2021Recursive Contour Saliency Blending Network for Accurate Salient Object Detectioncited by 20
- 2021Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Imagescited by 16
- 2022Disentangle Saliency Detection into Cascaded Detail Modeling and Body Fillingcited by 1
Built on by
Not cited yet.