OffRoadTranSeg: Semi-Supervised Segmentation using Transformers on OffRoad environments
This addresses scene understanding in unstructured outdoor environments for autonomous driving, offering a novel semi-supervised approach to reduce labeling needs.
The paper tackles offroad segmentation for autonomous driving by proposing OffRoadTranSeg, a semi-supervised framework using transformers and automatic data selection, which outperforms state-of-the-art models on RELLIS-3D and RUGD datasets and solves class imbalance issues.
We present OffRoadTranSeg, the first end-to-end framework for semi-supervised segmentation in unstructured outdoor environment using transformers and automatic data selection for labelling. The offroad segmentation is a scene understanding approach that is widely used in autonomous driving. The popular offroad segmentation method is to use fully connected convolution layers and large labelled data, however, due to class imbalance, there will be several mismatches and also some classes may not be detected. Our approach is to do the task of offroad segmentation in a semi-supervised manner. The aim is to provide a model where self supervised vision transformer is used to fine-tune offroad datasets with self-supervised data collection for labelling using depth estimation. The proposed method is validated on RELLIS-3D and RUGD offroad datasets. The experiments show that OffRoadTranSeg outperformed other state of the art models, and also solves the RELLIS-3D class imbalance problem.