Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection
This work addresses the challenge of better integrating RGB and depth data for salient object detection, which is important for applications like robotics and image processing, but it appears incremental as it builds on existing fusion techniques.
The paper tackles the problem of RGB-D salient object detection by proposing a method that integrates cross-modal features through dynamic filters and a hybrid loss function, achieving state-of-the-art performance on eight benchmark datasets with improvements across six metrics.
The main purpose of RGB-D salient object detection (SOD) is how to better integrate and utilize cross-modal fusion information. In this paper, we explore these issues from a new perspective. We integrate the features of different modalities through densely connected structures and use their mixed features to generate dynamic filters with receptive fields of different sizes. In the end, we implement a kind of more flexible and efficient multi-scale cross-modal feature processing, i.e. dynamic dilated pyramid module. In order to make the predictions have sharper edges and consistent saliency regions, we design a hybrid enhanced loss function to further optimize the results. This loss function is also validated to be effective in the single-modal RGB SOD task. In terms of six metrics, the proposed method outperforms the existing twelve methods on eight challenging benchmark datasets. A large number of experiments verify the effectiveness of the proposed module and loss function. Our code, model and results are available at \url{https://github.com/lartpang/HDFNet}.