TACO: Trash Annotations in Context for Litter Detection
It addresses the problem of litter detection for environmental monitoring, but is incremental as it focuses on dataset creation and baseline results.
The paper introduces TACO, an open dataset for litter detection and segmentation, and reports promising instance segmentation results using Mask R-CNN, achieving performance on a small dataset of 1500 images and 4784 annotations.
TACO is an open image dataset for litter detection and segmentation, which is growing through crowdsourcing. Firstly, this paper describes this dataset and the tools developed to support it. Secondly, we report instance segmentation performance using Mask R-CNN on the current version of TACO. Despite its small size (1500 images and 4784 annotations), our results are promising on this challenging problem. However, to achieve satisfactory trash detection in the wild for deployment, TACO still needs much more manual annotations. These can be contributed using: http://tacodataset.org/