**Region of Interest Warping**, or **RoIWarp**, is a form of [RoIPool](https://paperswithcode.com/method/roi-pooling) that is differentiable with respect to the box position. In practice, this takes the form of a RoIWarp layer followed by a standard [Max Pooling](https://paperswithcode.com/method/max-pooling) layer. The RoIWarp layer crops a feature map region and warps it into a target size by interpolation.

Inspired on the widely known [spatial squeeze and channel excitation (SE)](https://paperswithcode.com/method/squeeze-and-excitation-block) block, the sSE block performs channel squeeze and spatial excitation, to recalibrate the feature maps spatially and achieve more fine-grained image segmentation.

Channel Squeeze and Spatial Excitation

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks

RoIWarp

Instance-aware Semantic Segmentation via Multi-task Network Cascades

ZeRO-Offload is a sharded data parallel method for distributed training. It exploits both CPU memory and compute for offloading, while offering a clear path towards efficiently scaling on multiple GPUs by working with [ZeRO-powered data parallelism](https://www.paperswithcode.com/method/zero). The symbiosis allows ZeRO-Offload to maintain a single copy of the optimizer states on the CPU memory regardless of the data parallel degree. Furthermore, it keeps the aggregate communication volume between GPU and CPU, as well as the aggregate CPU computation a constant regardless of data parallelism, allowing ZeRO-Offload to effectively utilize the linear increase in CPU compute with the increase in the data parallelism degree.

Source	Instance-aware Semantic Segmentation via Multi-task Network Cascades
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com