GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

arXiv:2310.10375v2 Announce Type: replace-cross
Abstract: As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks, their suitability for vision tasks, which typically exhibit different structural properties in their data, is questionable. We argue that existing positional encoding schemes are suboptimal for 3D vision tasks, as they do not respect their underlying 3D geometric structure. Based on …

abstract arxiv attention cs.ai cs.cv cs.lg encoding geometry gta however information nlp positional encoding stat.ml tasks tokens transformers type view vision