CrossTransformers is a Transformer-based neural network architecture which can take a small number of labeled images and an unlabeled query, find coarse spatial correspondence between the query and the labeled images, and then infer class membership by computing distances between spatially-corresponding features.

The **Re-Attention Module** is an attention layer used in the [DeepViT](https://paperswithcode.com/method/deepvit) architecture which mixes the attention map with a learnable matrix before multiplying with the values. The motivation is to re-generate the attention maps to increase their diversity at different layers with negligible computation and memory cost. The authors note that traditional self-attention fails to learn effective concepts for representation learning in deeper layers of ViT -- attention maps become more similar and less diverse in deeper layers (attention collapse) - and this hinders the model from getting expected performance gain. Re-attention is implemented by:

$$
\operatorname{Re}-\operatorname{Attention}(Q, K, V)=\operatorname{Norm}\left(\Theta^{\top}\left(\operatorname{Softmax}\left(\frac{Q K^{\top}}{\sqrt{d}}\right)\right)\right) V
$$

where transformation matrix $\Theta$ is multiplied to the self-attention map $\textbf{A}$ along the head dimension.

Re-Attention Module

DeepViT: Towards Deeper Vision Transformer

CrossTransformers

CrossTransformers: spatially-aware few-shot transfer

**In-Place Activated Batch Normalization**, or **InPlace-ABN**, substitutes the conventionally used succession of [BatchNorm](https://paperswithcode.com/method/batch-normalization) + Activation layers with a single plugin layer, hence avoiding invasive framework surgery while providing straightforward applicability for existing deep learning frameworks. It approximately halves the memory requirements during training of modern deep learning models.

Source	CrossTransformers: spatially-aware few-shot transfer
Year	2000
Data Source	Papers with Code archive (CC BY-SA)