Submitted by Rohit Mohan.

Submission data

Full nameSelf-Supervised Model Adaptation for Multimodal Semantic Segmentation
DescriptionBenchmarking the SSMA mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner. The model was trained with the visual RGB image and the HHA encoded depth image as input to the network. The architecture consists of two modality-specific encoder streams that fuse intermediate encoder representations into a single decoder using the SSMA fusion mechanism which optimally combines complementary features.
Publication titleSelf-Supervised Model Adaptation for Multimodal Semantic Segmentation
Publication authorsAbhinav Valada, Rohit Mohan, Wolfram Burgard
Publication venueInternational Journal of Computer Vision, 2019
Publication URL
Input Data TypesUses Color,Uses Geometry        Uses 2D
Programming language(s)Python, Tensorflow
HardwareIntel Xeon E5 CPU, NVIDIA TITAN X (Pascal)
Source code or download URL
Submission creation date29 Dec, 2018
Last edited18 Jul, 2019

2D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow