TACO: Trash Annotations in Context for Litter Detection

By Pedro F. Proença, Pedro Simões. 2020

197 citations recorded by the source corpus.

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: this http URL

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering, Pollution, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

In Evaluation & Benchmarks

Citations in the corpus

ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes (2021, methodology): “Ze-roWaste Aug comprises a version of ZeroWaste-f in which frames were augmented with the objects of the rare metal and rigid plastic classes that were cropped out of TACO [48] dataset.”
FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters (2021, background): “The recently published TACO dataset [42] contains multi-class annotated photos of wastes in the wild.”
Robotic Waste Sorting Technology: Toward a Vision-Based Categorization System for the Industrial Robotic Separation of Recyclable Waste (2021, background): “To the best of our knowledge, there are only two open source data sets, namely, TrashNet [16] and Taco [17], that are available for public use.”