Robust Training

Deep Equilibrium Models

Introduced by Bai et al. in Deep Equilibrium Models

A new kind of implicit models, where the output of the network is defined as the solution to an "infinite-level" fixed point equation. Thanks to this we can compute the gradient of the output without activations and therefore with a significantly reduced memory footprint.

Source: Deep Equilibrium Models


Paper Code Results Date Stars


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign