In this example, we will build a multi-label text classifier to predict the subject areas of arXiv papers from their abstract bodies. This type of classifier can be useful for conference submission portals like OpenReview.
A “point cloud” is an important type of data structure for storing geometric shape data. Due to its irregular format, it’s often transformed into regular 3D voxel grids or collections of images before being used in deep learning applications, a step which makes the data unnecessarily large.
Semantic segmentation, with the goal to assign semantic labels to every pixel in an image, is an essential computer vision task. In this example, we implement the DeepLabV3+ model for multi-class semantic segmentation, a fully-convolutional architecture that performs well on semantic segmentation benchmarks.