Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks

@inproceedings{Wang2016LearningCA,
  title={Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks},
  author={Jinghua Wang and Zhenhua Wang and Dacheng Tao and Simon See and Gang Wang},
  booktitle={ECCV},
  year={2016}
}
The class average accuracies of different methods on the NYU V2: The Proposed Network Structure The model has a convolutional network and deconvolutional network for each modality, as well as a feature transformation network. In this structure, 1. The RGB and depth convolutional network have the same structure; 2. The deconvolutional networks are the mirrored version of the convolutional networks; 3. The feature transformation network extracts common features and modality specific features; 4… CONTINUE READING
Highly Cited
This paper has 23 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 11 times over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 16 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 39 references

Similar Papers

Loading similar papers…