Assisting RGB and depth salient object detection with nonconvolutional encoder: an improvement approach
- 1 March 2024
- journal article
- research article
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 33 (02) , 023036-16
Abstract
RGB-D salient object detection is a challenging task in computer vision, and deep architectures have been widely adopted in the previous studies. However, current convolutional neural network (CNN)-based models struggle with capturing global long-distance features efficiently, whereas transformer-based methods are computationally intensive. To address these limitations, we propose a nonconvolutional feature encoder. This encoder captures long-distance dependencies while reducing computation costs, making it a potential alternative to CNNs and transformers. Additionally, we introduce a spatial info enhancing mechanism to overcome weakened local information while capturing long-range dependencies. This mechanism balances local and global information at different expansion rates by exploring multiscale feature fusion in the feature maps. Furthermore, we introduce a spatial info sensing module to enhance the compatibility of multimodal features in long-range dependencies and extract informative cues from depth features. Through comprehensive experiments on four widely used datasets, we demonstrate that our proposed involution encoder significantly outperforms previous state-of-the-art RGB-D salient object detection methods based on CNNs in four key metrics. Compared to transformer-based methods, our approach balances speed and efficiency favorably.Keywords
This publication has 64 references indexed in Scilit:
- FANet: Feature aggregation network for RGBD saliency detectionSignal Processing: Image Communication, 2022
- Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection2020
- End-to-End Object Detection with Transformers2020
- Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency Detection2020
- Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency mapsPattern Recognition, 2020
- Salient object detection for RGB-D image by single stream recurrent convolution neural networkNeurocomputing, 2019
- A multilayer backpropagation saliency detection algorithm and its applicationsMultimedia Tools and Applications, 2018
- RGBD co-saliency detection via multiple kernel boosting and fusionMultimedia Tools and Applications, 2018
- RGBD Salient Object Detection: A Benchmark and Algorithms2014
- Leveraging stereopsis for saliency analysis2012