Self-Supervised Model Adaptation for Multimodal Semantic Segmentation

11 Aug 2018Abhinav ValadaRohit MohanWolfram Burgard

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Semantic Segmentation Cityscapes test SSMA Mean IoU (class) 82.3% # 10
Semantic Segmentation Cityscapes test AdapNet++ Mean IoU (class) 81.24% # 19
Semantic Segmentation Freiburg Forest SSMA Mean IoU 84.18 # 1
Semantic Segmentation Freiburg Forest AdapNet++ Mean IoU 83.09 # 2
Scene Recognition ScanNet SSMA Average Recall 54.28 # 1
Semantic Segmentation ScanNetV2 SSMA Mean IoU 57.7 # 1
Semantic Segmentation ScanNetV2 AdapNet++ Mean IoU 50.3 # 2
Semantic Segmentation SUN-RGBD SSMA Mean IoU 45.73 # 1
Semantic Segmentation SUN-RGBD AdapNet++ Mean IoU 38.40 # 2
Semantic Segmentation SYNTHIA-CVPR’16 AdapNet++ Mean IoU 87.87 # 2
Semantic Segmentation SYNTHIA-CVPR’16 SSMA Mean IoU 92.10 # 1