What is the difference between the different PointGPT-S models?

[m-a-x-c]

Here are the different PointGPT-S models:

PointGPT-S Models

Task	Dataset	Config	Acc.	Download
Pre-training	ShapeNet	pretrain.yaml	N.A.	here
Classification	ScanObjectNN	finetune_scan_hardest.yaml	86.9%	here
Classification	ScanObjectNN	finetune_scan_objbg.yaml	91.6%	here
Classification	ScanObjectNN	finetune_scan_objonly.yaml	90.0%	here
Classification	ModelNet40(1k)	finetune_modelnet.yaml	94.0%	here
Classification	ModelNet40(8k)	finetune_modelnet_8k.yaml	94.2%	here
Part segmentation	ShapeNetPart	segmentation	86.2% mIoU	here

I thought all the classification models were trasfered to the ScanObjectNN dataset then evaluated against {OBJ_BG, OBJ_ONLY, PB_T50_RS, ModelNet40-1k, ModelNet40-8k}. So why is there five different links for classification models? Shouldn't there be only one link because they were all transfer learned on ScanObjectNN?

Please let me know where I have misunderstood. Thanks.

[CGuangyan-BIT]

We start by pretraining on ShapeNet to obtain pre-trained models, and then fine-tune them on various scenarios within different datasets to obtain network parameters for different tasks. Take ScanObjectNN, for instance; it comprises three distinct scenarios, with each scenario corresponding to a specific set of network parameters.

[m-a-x-c]

Thank you.