Seesaw Loss for Long-Tailed Instance Segmentation

Seesaw Loss：长尾实例分割中的平衡损失.

Equalization Loss for Long-Tailed Object Recognition

Equalization Loss：长尾目标检测中的均衡损失.

Class-Balanced Loss Based on Effective Number of Samples

Class-balanced Loss：基于有效样本数的类别平衡损失.

Decoupling Representation and Classifier for Long-Tailed Recognition

将长尾分布的图像分类问题解耦为表示学习和分类.

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

ELECTRA：判别式的预训练语言模型.

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

ACNet：深度网络重参数化.