Joint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps [pdf]
A paper about how to use OSM to improve satellite image segmentation.
Winning Solution for the Spacenet Challenge: Joint Learning with OpenStreetMap [link]
The winning solution for the Spacenet Challenge (V2).
From CVPR 2018. Applying domain adaptation on the outputspace.
From CVPR 2019. Combine Segment Net and Context Net.
Use context information to improve performance.
Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training [pdf]
ECCV 2018
Learning to Adapt Structured Output Space for Semantic Segmentation [pdf]
CVPR 2018
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification [pdf]
CVPR 2019
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation [pdf]
CVPR 2019
Demystifying Neural Style Transfer [pdf]
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization [pdf]
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation [pdf]
DADA: Depth-aware Domain Adaptation in Semantic Segmentation [pdf]
Domain-invariant Learning using Adaptive Filter Decomposition [pdf]
Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation [pdf]
Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation [pdf]
ICCV 2019 Best Paper nomination