Re:Minimum bipartite matching via Riemann optimization
by marco_z on Wednesday January 08, 2025 @03:22PM
(#42638062)
It's incredible how many algorithms can be made differentiable end-to-end.
E.g. in https://arxiv.org/abs/1905.11885 "Differentiable ranks and sorting using optimal transport" they show how a relaxation of an array sorting procedure leads to differentiable rank statistics (quantiles etc.). The underlying theory is quite close to what I show in the blog post.
In DETR they don't actually use a differentiable Hungarian algorithm, it's only used to score their neural predictions outside of the training loop IIUC.
E.g. in https://arxiv.org/abs/1905.11885 "Differentiable ranks and sorting using optimal transport" they show how a relaxation of an array sorting procedure leads to differentiable rank statistics (quantiles etc.). The underlying theory is quite close to what I show in the blog post.
In DETR they don't actually use a differentiable Hungarian algorithm, it's only used to score their neural predictions outside of the training loop IIUC.