Addressing appearance change in outdoor robotics with adversarial domain adaptation
Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it will deliver degraded performance in application domains that...
Main Authors: | Wulfeier, M, Bewley, A, Posner, H |
---|---|
Format: | Conference item |
Published: |
Institute of Electrical and Electronics Engineers
2017
|
Similar Items
-
Incremental adversarial domain adaptation for continually changing environments
by: Wulfmeier, M, et al.
Published: (2018) -
Deep adversarial domain adaptation network
by: Lan Wu, et al.
Published: (2020-10-01) -
Neural stethoscopes: Unifying analytic, auxiliary and adversarial network probing
by: Fuchs, F, et al.
Published: (2018) -
Adaptive restoration of pedestrian appearance in the spatiotemporal domain
by: Yunzuo Zhang, et al.
Published: (2022-01-01) -
Aspect-augmented Adversarial Networks for Domain Adaptation
by: Zhang, Yuan, et al.
Published: (2021)