A method to disentangle pose from other factors in a scene.

**Reversible Residual Blocks** are skip-connection blocks that learn *reversible* residual functions with reference to the layer inputs. It is proposed as part of the [RevNet](https://paperswithcode.com/method/revnet) CNN architecture. Units in each layer are partitioned into two groups, denoted $x\_{1}$ and $x\_{2}$; the authors find what works best is partitioning the channels. Each reversible block takes inputs $\left(x\_{1}, x\_{2}\right)$ and produces outputs $\left(y\_{1}, y\_{2}\right)$ according to the following additive coupling rules – inspired by the transformation in [NICE](https://paperswithcode.com/method/nice) (nonlinear independent components estimation) – and residual functions $F$ and $G$ analogous to those in standard [ResNets](https://paperswithcode.com/method/resnet):

$$y\_{1} = x\_{1} + F\left(x\_{2}\right)$$
$$y\_{2} = x\_{2} + G\left(y\_{1}\right)$$

Each layer’s activations can be reconstructed from the next layer’s activations as follows:

$$ x\_{2} = y\_{2} − G\left(y\_{1}\right)$$
$$ x\_{1} = y\_{1} − F\left(x\_{2}\right)$$

Reversible Residual Block

The Reversible Residual Network: Backpropagation Without Storing Activations

Pose Disentangling

Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

**Instruction Pointer Attention Graph Neural Network**, or **IPA-GNN**, is a learning-interpreter neural network (LNN) based on GNNs for learning to execute programmes. It achieves improved systematic generalization on the task of learning to execute programs using control flow graphs. The model arises by considering RNNs operating on program traces with branch decisions as latent variables. The IPA-GNN can be seen either as a continuous relaxation of the RNN model or as a GNN variant more tailored to execution.

Source	Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
Year	2000
Data Source	Papers with Code archive (CC BY-SA)