Pointy, a lightweight transformer trained on 39k point clouds, outperforms larger foundation models trained on 200k+ samples and nears SOTA from million-sample multimodal models.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Data augmentations in contrastive learning are proved to be point estimates of positive-incentive noise, enabling a new learnable π-noise generator framework for augmentations.
citing papers explorer
-
Pointy - A Lightweight Transformer for Point Cloud Foundation Models
Pointy, a lightweight transformer trained on 39k point clouds, outperforms larger foundation models trained on 200k+ samples and nears SOTA from million-sample multimodal models.
-
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
Data augmentations in contrastive learning are proved to be point estimates of positive-incentive noise, enabling a new learnable π-noise generator framework for augmentations.