ResNet-101 is a deep convolutional neural network architecture developed by Microsoft Research. It is a 101-layer convolutional neural network with residual blocks, which are designed to improve the accuracy of deep neural networks. The architecture was developed as part of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and has been used in many applications ranging from image classification to object detection. ResNet-101 has achieved state-of-the-art performance on various tasks such as image classification, object detection, and semantic segmentation.