This paper presents an approach to address data scarcity problems in underwater image datasets for visual detection of marine debris. The proposed approach relies on a two-stage variational autoencoder (VAE) and a binary classifier to evaluate the generated imagery for quality and realism. From the images generated by the two-stage VAE, the binary classifier selects good quality images and augments the given dataset with them. Lastly, a multi-class classifier is used to evaluate the impact of the augmentation process by measuring the accuracy of an object detector trained on combinations of real and generated trash images. Our results show that the classifier trained with the augmented data outperforms the one trained only with the real data. This approach will not only be valid for the underwater trash classification problem presented in this paper, but it will also be useful for any data-dependent task for which collecting more images is challenging or infeasible.
|Original language||English (US)|
|Title of host publication||2020 IEEE International Conference on Robotics and Automation, ICRA 2020|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||7|
|State||Published - May 2020|
|Event||2020 IEEE International Conference on Robotics and Automation, ICRA 2020 - Paris, France|
Duration: May 31 2020 → Aug 31 2020
|Name||Proceedings - IEEE International Conference on Robotics and Automation|
|Conference||2020 IEEE International Conference on Robotics and Automation, ICRA 2020|
|Period||5/31/20 → 8/31/20|
Bibliographical noteFunding Information:
We are thankful to Owen Queeglay, Kevin Orpen, and Kimberly Barthelemy for their assistance with image labeling. Jungseok Hong and Michael Fulton are supported by UMII-MnDRIVE and National Science Foundation GRFP fellowships, respectively.
© 2020 IEEE.