PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmark
This addresses memory and legal constraints in 3D computer vision applications by enabling class incremental learning without storing previous data, though it appears incremental as it adapts existing concepts to point clouds.
The paper tackles the problem of catastrophic forgetting in class incremental learning for 3D point clouds by proposing PointCLIMB, an exemplar-free benchmark, and demonstrates results on the ModelNet40 dataset with performance evaluations of various backbones.
Point clouds offer comprehensive and precise data regarding the contour and configuration of objects. Employing such geometric and topological 3D information of objects in class incremental learning can aid endless application in 3D-computer vision. Well known 3D-point cloud class incremental learning methods for addressing catastrophic forgetting generally entail the usage of previously encountered data, which can present difficulties in situations where there are restrictions on memory or when there are concerns about the legality of the data. Towards this we pioneer to leverage exemplar free class incremental learning on Point Clouds. In this paper we propose PointCLIMB: An exemplar Free Class Incremental Learning Benchmark. We focus on a pragmatic perspective to consider novel classes for class incremental learning on 3D point clouds. We setup a benchmark for 3D Exemplar free class incremental learning. We investigate performance of various backbones on 3D-Exemplar Free Class Incremental Learning framework. We demonstrate our results on ModelNet40 dataset.