Pseudo-labeling as a boost in waste classification task

Self-training method relies on making inference on unlabeled data and using created pseudo-labels in further training.

Detect waste with Transformer

In comparison to well-known two- or one-stage detectors, DETR does not need to set the number of anchor boxes or even threshold for NMS algorithm.

One to rule them all - combination of few datasets of waste

Neural networks can be useful in case of detecting trash in image, but they require collecting a large and good quality data.

Comparing waste detection approaches on extended TACO dataset

Differentiating waste instances under a single class label is challenging task

Basic metrics to compare waste detection models

Evaluation metrics that data scientists should know