ADA-AT/DT: An Adversarial Approach for Cross-Domain and Cross-Task Knowledge Transfer

We deal with the problem of cross-task and cross-domain knowledge transfer in the realm of scene understanding for autonomous vehicles. We consider the scenario where supervision is available for a pair of tasks in a source domain while it is available for only one of the tasks in the target domain. We develop a novel framework called ADA-AT/DT based on the adversarial training strategy to ensure that the domain-gaps are minimized for the common cross-domain supervised task and perform experiments on a transformation mapping similar to U-Net to ensure maximum exploitation of features for task transfer.

Please find the paper, supplementary material, video, and presentation.

If you find this work useful, please cite our paper

@InProceedings{Chavhan_2021_WACV,
    author    = {Chavhan, Ruchika and Jha, Ankit and Banerjee, Biplab and Chaudhuri, Subhasis},
    title     = {ADA-AT/DT: An Adversarial Approach for Cross-Domain and Cross-Task Knowledge Transfer},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    month     = {January},
    year      = {2021},
    pages     = {3502-3511}
}