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 URL
Input Data TypesUses Color,Uses Geometry        Uses 2D
Programming language(s)Python, Tensorflow
HardwareIntel Xeon E5 CPU, NVIDIA TITAN X (Pascal)
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