The **Local Relation Network** (**LR-Net**) is a network built with local relation layers which represent a feature image extractor. This feature extractor adaptively determines aggregation weights based on the compositional relationship of local pixel pairs.

Unsupervised knowledge distillation from a pretrained language model to *itself*, by alternating between its bi- and cross-encoder forms.

Trans-Encoder

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

LRNet

Local Relation Networks for Image Recognition

**GreedyNAS-C** is a convolutional neural network discovered using the [GreedyNAS](https://paperswithcode.com/method/greedynas) [neural architecture search](https://paperswithcode.com/method/neural-architecture-search) method. The basic building blocks used are inverted residual blocks (from [MobileNetV2](https://paperswithcode.com/method/mobilenetv2)) and squeeze-and-excitation blocks.

Source	Local Relation Networks for Image Recognition
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com