At the heart of foundation models is the philosophy of "more is different", exemplified by the astonishing success in computer vision and natural language

Specifically,theyreduce theproblem of optimization with a first-order oracle to a mean estimation problem whose probability of error is lowerbounded usingFano'smethod (cf.[31]).

Calibrated probabilistic classifiers are models whose predicted probabilities can directly be interpreted as uncertainty estimates. It has been shown recently that deep neural networks arepoorly calibratedandtend tooutput overconfident predictions.

In this paper, we propose a novel method to enhance vision Graph Neural Networks (GNNs) by an additional capability, missing from any other previous works. That is, to have nodes that are constructed for spatial reasoning and can adapt to the current input. Prior works are limited to having either nodes attached to semantic attention maps [4]or attached to fixed locations such as grids[5,3,6].

In this paper, we propose a novel method to enhance vision Graph Neural Networks (GNNs) by an additional capability, missing from any other previous works. That is, to have nodes that are constructed for spatial reasoning and can adapt to the current input. Prior works are limited to having either nodes attached to semantic attention maps [4]or attached to fixed locations such as grids[5,3,6].