Autoencoder based inter-vehicle generalization for in-cabin occupant classification
Common domain shift problem formulations consider the integration of multiple source
domains, or the target domain during training. Regarding the generalization of machine …
domains, or the target domain during training. Regarding the generalization of machine …
Illumination normalization by partially impossible encoder-decoder cost function
SD Da Cruz, B Taetz, T Stifter… - Proceedings of the …, 2021 - openaccess.thecvf.com
Images recorded during the lifetime of computer vision based systems undergo a wide
range of illumination and environmental conditions affecting the reliability of previously …
range of illumination and environmental conditions affecting the reliability of previously …
Autoencoder for synthetic to real generalization: From simple to more complex scenes
SD Da Cruz, B Taetz, T Stifter… - 2022 26th International …, 2022 - ieeexplore.ieee.org
Learning on synthetic data and transferring the resulting properties to their real counterparts
is an important challenge for reducing costs and increasing safety in machine learning. In …
is an important challenge for reducing costs and increasing safety in machine learning. In …
Towards Reliable Computer Vision Feature Extraction by Novel Autoencoder Methods
S Dias da Cruz - 2023 - kluedo.ub.rptu.de
The generally unsupervised nature of autoencoder models implies that the main training
metric is formulated as the error between input images and their corresponding …
metric is formulated as the error between input images and their corresponding …
[PDF][PDF] Towards Reliable Computer Vision Feature Extraction by Novel Autoencoder Methods
SD DA CRUZ - kluedo.ub.rptu.de
The generally unsupervised nature of autoencoder models implies that the main training
metric is formulated as the error between input images and their corresponding …
metric is formulated as the error between input images and their corresponding …