Transfer Learning with Point Transformers

arXiv:2404.00846v1 Announce Type: cross
Abstract: Point Transformers are near state-of-the-art models for classification, segmentation, and detection tasks on Point Cloud data. They utilize a self attention based mechanism to model large range spatial dependencies between multiple point sets. In this project we explore two things: classification performance of these attention based networks on ModelNet10 dataset and then, we use the trained model to classify 3D MNIST dataset after finetuning. We also train the model from scratch on 3D MNIST dataset …

abstract art arxiv attention classification cloud cloud data cs.cv cs.lg data dataset dependencies detection explore multiple near networks performance project segmentation spatial state state-of-the-art models tasks transfer transfer learning transformers type