de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons180812

He,  Yang
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44237

Chiu,  Wei-Chen
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons180612

Keuper,  Margret
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44451

Fritz,  Mario
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1604.02388.pdf
(Preprint), 2MB

Supplementary Material (public)
There is no public supplementary material available
Citation

He, Y., Chiu, W.-C., Keuper, M., & Fritz, M. (2016). RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling. Retrieved from http://arxiv.org/abs/1604.02388.


Cite as: http://hdl.handle.net/11858/00-001M-0000-002B-063C-5
Abstract
Beyond the success in classification, neural networks have recently shown strong results on pixel-wise prediction tasks like image semantic segmentation on RGBD data. However, the commonly used deconvolutional layers for upsampling intermediate representations to the full-resolution output still show different failure modes, like imprecise segmentation boundaries and label mistakes in particular on large, weakly textured objects (e.g. fridge, whiteboard, door). We attribute these errors in part to the rigid way, current network aggregate information, that can be either too local (missing context) or too global (inaccurate boundaries). Therefore we propose a data-driven pooling layer that integrates with fully convolutional architectures and utilizes boundary detection from RGBD image segmentation approaches. We extend our approach to leverage region-level correspondences across images with an additional temporal pooling stage. We evaluate our approach on the NYU-Depth-V2 dataset comprised of indoor RGBD video sequences and compare it to various state-of-the-art baselines. Besides a general improvement over the state-of-the-art, our approach shows particularly good results in terms of accuracy of the predicted boundaries and in segmenting previously problematic classes.