**GreedyNAS-A** 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.

XLM-R

Unsupervised Cross-lingual Representation Learning at Scale

GreedyNAS-A

GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet

**CascadePSP** is a general segmentation refinement model that refines any given segmentation from low to high resolution. The model takes as input an initial mask that can be an output of any algorithm to provide a rough object location. Then the CascadePSP will output a refined mask. The model is designed in a cascade fashion that generates refined segmentation in a coarse-to-fine manner. Coarse outputs from the early levels predict object structure which will be used as input to the latter levels to refine boundary details.

Source	GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet
Year	2000
Data Source	Papers with Code archive (CC BY-SA)