##Goal:
We welcome you to the BugNIST challenge, which is part of the FGVC11 workshop at CVPR 2024. Here you will compete in detecting and classifying objects in volumes under domain shift and hereby contribute to advancing methods for the analysis of volumetric data. Based on volumes containing one bug each, your task is to train a model that can detect and classify bugs in volumes that contain several bugs mixed with other materials. 

##Collaborative paper!
After the FGVC workshop, we will collect short descriptions from the participating teams to write a collaborative paper on approaches for detection under domain shift. We will reach out to you for your input.

##Baseline implementation!
There is now a baseline implementation for detection available. See the *U-Net baseline* under the *Code* tab.

##Why does it matter?
In volumetric imaging, it is often necessary to detect and classify objects that are densely packed in a mixture of other objects or materials that are not of interest. Annotating such data is tedious and difficult, and instead, it is much easier to scan some representative examples of the type of objects that should be detected. The problem is that individually scanned objects are placed in a context that is very different from the mixed objects that we wish to detect. This is a domain shift, where the objects of interest have the same appearance, but the context surrounding the objects is different.

To promote the development of new methods for domain adaptation in volumetric scans, we have created the BugNIST dataset, which is the basis for the BugNIST challenge. The dataset is based on 12 types of bugs such as larvae, pupae, grasshoppers, etc. The training data is more than 700 micro-CT scans of individual bugs of each type, whereas the test data is mixtures.