Enhance 2D detection and labeling accuracy through the implementation of optimized bounding boxes.
![](https://vinlab.io/wp-content/uploads/2023/02/Screenshot-2023-02-20-at-17.43.06-1024x724.png)
Elevate the accuracy of AI models by utilizing polygon annotations for precise object identification.
Semantic segmentation associates every pixel of an image with a class label such as bones, internal organs, nodules and so on. It treats multiple objects of the same class as a single entity.
Instance segmentation treats multiple findings of the same class as distinct individual instances.