This is the code for the paper DF2Net: A Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification(AAAI 2018).
- Install prerequsites for caffe. The caffe version we use can be found in our
caffe_dev
repo. - Add the loss layers to the
caffe_dev
source and include path. - Compile the
caffe_dev
Github submodule
You can download our trained model on SUN RGB-D Dataset and NYU Dataset V2 at Baidu Netdisk or Google Driver.
We use the Saurabh Gupta's code to convert the depth images. We also release our converted HHA images of SUN RGB-D Dataset and NYU Depth V2 Dataset at Google Driver.