Unifying convolution and transformer: A dual stage network equipped with cross-interactive feature fusion and edge guidance for RGB-D salient object detection
Python 3.7, Pytorch 0.4.0+, Cuda 10.0, TensorboardX 2.0, opencv-python
Train data link: https://drive.google.com/file/d/1yjtYG_05Nj7_G-DO1DygBhlkk_U3vDwo/view?usp=sharing
Test data link: https://drive.google.com/file/d/1pGq4nehuv7gJDENEWD2cuKTz937tCoVO/view?usp=sharing
Validation data link: https://drive.google.com/file/d/13FRrzznTAnVAIdCeq38s1STfk1JOS6it/view?usp=sharing
Depth maps are not in HHA converted format. The depth images can be made to pass through HHA algorithm, as given in tohha.py
We provide testing results of 7 datasets which can be accessed at https://drive.google.com/file/d/1KpDca0PnC4vL0M13HALYWK1wjkgZ4Eev/view?usp=sharing
Evaluate the result maps: You can evaluate the result maps using Python_Eval