Extensive analysis and experiments on SUN RGB-D Dataset and NYU Depth Dataset V2 show the superiority of DF2Net over other state-of-the-art methods in RGB-D indoor scene classification task. In the second stage, we design a novel discriminative fusion network which is able to learn correlative features of multiple modalities and distinctive features of each modality. In the first stage, to better represent scene in each modality, a deep multi-task network is constructed to simultaneously minimize the structured loss and the softmax loss. To address these problems, this paper proposes a Discriminative Feature Learning and Fusion Network (DF2Net) with two-stage training. However, these pipelines do not explicitly consider intra-class and inter-class similarity as well as inter-modal intrinsic relationships. Most existing works learn representation for classification by training a deep network with softmax loss and fuse the two modalities by simply concatenating the features of them. 2) Fusing the complementary cues in RGB and Depth is nontrivial since there are large semantic gaps between the two modalities. 1) Learning robust representation for indoor scene is difficult because of various objects and layouts. It is a very challenging task due to two folds. This paper focuses on the task of RGB-D indoor scene classification. Request to Reproduce Copyrighted Materials.Code of Conduct for Conferences and Events.The Role of Intelligent Systems in the National Information Infrastructure.A Report to ARPA on Twenty-First Century Intelligent Systems.Presidential Panel on Long-Term AI Futures.Patrick Henry Winston Outstanding Educator Award.
Award for Artificial Intelligence for the Benefit of Humanity.
0 kommentar(er)
