Submitted by Rohit Mohan.

Submission data

Full nameSE-ResNeXt-SSMA
DescriptionSE-ResNeXt-101 backbone with multimodal SSMA fusion of visual RGB images (top-down views) and colorized depth maps as input to the network.
Publication titleSelf-Supervised Model Adaptation for Multimodal Semantic Segmentation
Publication authorsAbhinav Valada, Rohit Mohan, Wolfram Burgard
Publication venuearXiv
Publication URLhttps://arxiv.org/abs/1808.03833
Input Data TypesUses Color,Uses Geometry        Uses 2D
Programming language(s)Python, Tensorflow
HardwareIntel Xeon E5 CPU, NVIDIA TITAN X (Pascal)
Websitehttp://deepscene.cs.uni-freiburg.de
Submission creation date18 Jan, 2019
Last edited20 Jan, 2019

Scene type classification results



Infoavg recallapartmentbathroombedroom / hotelbookstore / libraryconference roomcopy/mail roomhallwaykitchenlaundry roomliving room / loungemiscofficestorage / basement / garage
0.4980.0000.8120.9410.5000.5000.5000.5000.4290.5000.6670.5000.6250.000