Densely Deformable Efficient Salient Object Detection Network
This work addresses efficiency and generalization challenges in SOD for computer vision applications, but it is incremental as it builds on existing deformable convolution techniques.
The paper tackles the problem of limited generalization and high computational complexity in RGB-D Salient Object Detection (SOD) by proposing a Densely Deformable Network (DDNet) that uses deformable convolutions for efficient SOD, achieving competitive results against 22 methods on a recent dataset and highlighting generalization issues with a new cross-dataset.
Salient Object Detection (SOD) domain using RGB-D data has lately emerged with some current models' adequately precise results. However, they have restrained generalization abilities and intensive computational complexity. In this paper, inspired by the best background/foreground separation abilities of deformable convolutions, we employ them in our Densely Deformable Network (DDNet) to achieve efficient SOD. The salient regions from densely deformable convolutions are further refined using transposed convolutions to optimally generate the saliency maps. Quantitative and qualitative evaluations using the recent SOD dataset against 22 competing techniques show our method's efficiency and effectiveness. We also offer evaluation using our own created cross-dataset, surveillance-SOD (S-SOD), to check the trained models' validity in terms of their applicability in diverse scenarios. The results indicate that the current models have limited generalization potentials, demanding further research in this direction. Our code and new dataset will be publicly available at https://github.com/tanveer-hussain/EfficientSOD