Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification
This addresses the domain shift problem for in-cabin occupant classification, enabling generalization across different vehicles without requiring multiple source domains or target data during training, though it is incremental in its method.
The paper tackles the problem of occupant classification in car interiors when training on a single vehicle and deploying to unseen vehicles, proposing an autoencoder-based approach that matches or outperforms standard classification models and can transform images from unknown vehicles into the known domain.
Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the criterion of training in a single vehicle: without access to the target distribution of the vehicle the model would be deployed to, neither with access to multiple vehicles during training. We performed an investigation on the SVIRO dataset for occupant classification on the rear bench and propose an autoencoder based approach to improve the transferability. The autoencoder is on par with commonly used classification models when trained from scratch and sometimes out-performs models pre-trained on a large amount of data. Moreover, the autoencoder can transform images from unknown vehicles into the vehicle it was trained on. These results are corroborated by an evaluation on real infrared images from two vehicle interiors.