SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers — mentioned by arketyp

Thu, 25 Nov 2021 11:56:23 GMT

Transformers are exciting as they seem to work on all types of modalities, including vision [1]. It makes me wonder if the transformer module captures some essence of the minicolumn structure found all over the neocortex that Jeff Hawkins raves about, citing Vernon Mountcastle. Hawkins et al talk about grid cells nowadays, location; maybe attention and context is the generalization of such a notion. [1] https://arxiv.org/abs/2105.15203

Paper and discussion history. A mention is not an endorsement.

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers · HackerPapers discussions

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers — mentioned by arketyp