We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vision transformers have become one of the most important models for computer vision tasks. Although they outperform prior works, they require heavy computational resources on a scale that is quadratic to $N$. This is a major drawback of the traditional self-attention (SA) algorithm. Here, we propose the Unit Force Operated Vision Transformer (UFO-ViT), a novel SA mechanism that has linear complexity. The main approach of this work is to eliminate nonlinearity from the original SA. We factorize the matrix multiplication of the SA mechanism without complicated linear approximation. By modifying only a few lines of code from the original SA, the proposed models outperform most transformer-based models on image classification and dense prediction tasks on most capacity regimes.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.14382")
get_code_for_paper("2109.14382")
have("2109.14382")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.14382.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.14382)
Connect an agent — have() is free.