YOLO in the Dark - Domain Adaptation Method for Merging Multiple Models

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12366)


Generating models to handle new visual tasks requires additional datasets, which take considerable effort to create. We propose a method of domain adaptation for merging multiple models with less effort than creating an additional dataset. This method merges pre-trained models in different domains using glue layers and a generative model, which feeds latent features to the glue layers to train them without an additional dataset. We also propose a generative model that is created by distilling knowledge from pre-trained models. This enables the dataset to be reused to create latent features for training the glue layers. We apply this method to object detection in a low-light situation. The YOLO-in-the-Dark model comprises two models, Learning-to-See-in-the-Dark model and YOLO. We present the proposed method and report the result of domain adaptation to detect objects from RAW short-exposure low-light images. The YOLO-in-the-Dark model uses fewer computing resources than the naive approach.


Knowledge distillation Domain adaptation Object detection 


  1. 1.
    Chang, W.G., You, T., Seo, S., Kwak, S., Han, B.: Domain-specific batch normalization for unsupervised domain adaptation. In: CVPR 2019 (2019)Google Scholar
  2. 2.
    Chen, C., Chen, Q., Xu, J., Koltun, V.: Learning to see in the dark. In: CVPR 2018 (2018)Google Scholar
  3. 3.
    Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: Advances in Neural Information Processing Systems 30, pp. 742–751 (2017)Google Scholar
  4. 4.
    Everingham, M., Gool, L.V., Williams, C., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) results. In: VOC 2012 (2012)Google Scholar
  5. 5.
    Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv:1503.02531
  6. 6.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the Advances Neural Information Processing Systems 25 (NIPS), pp. 1097–1105 (2012)Google Scholar
  7. 7.
    Lin, T.Y., et al.: Microsoft coco: common objects in context (2014). arXiv:1405.0312
  8. 8.
    Loh, Y.P., Chan, C.S.: Getting to know low-light images with the exclusively dark dataset. Comput. Vis. Image Underst. 178, 30–42 (2019). Scholar
  9. 9.
    Luo, J., Xu, Y., Tang, C., Lv, J.: Learning inverse mapping by autoencoder based generative adversarial nets (2017). arXiv:1703.10094
  10. 10.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR 2016 (2016)Google Scholar
  11. 11.
    Redmon, J., Farhadi, A.: Yolov3: an incremental improvement (2018). arXiv:1804.02767
  12. 12.
    Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: hints for thin deep nets (2014). arXiv:1412.6550
  13. 13.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI (2015)Google Scholar
  14. 14.
    Teng, Y., Choromanska, A., Bojarski, M.: Invertible autoencoder for domain adaptation (2018). arXiv:1802.06869
  15. 15.
    Xie, S., Zheng, Z., Chen, L., Chen, C.: Learning semantic representations for unsupervised domain adaptation. In: ICML 2018 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Socionext Inc.KyotoJapan
  2. 2.Osaka UniversityOsakaJapan

Personalised recommendations