MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution — mentioned by 317070

Wed, 29 May 2024 21:34:01 GMT

I checked, and on the 28th of May, arXiv has seen 14 submissions with "transformer" in the title, and I found 3 of them with proposals tested on larger datasets (I did not check all of them, there might have been more than these three). https://arxiv.org/pdf/2405.18240 https://arxiv.org/abs/2405.17951 https://arxiv.org/pdf/2405.17821

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

MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution · HackerPapers discussions

MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution — mentioned by 317070