KeepAugment: A Simple Information-Preserving Data Augmentation Approach

KeepAugment：提高保真度的图像增强方法.

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

BART: 用于自然语言生成、翻译和理解的去噪序列到序列预训练模型.

ReZero is All You Need: Fast Convergence at Large Depth

你只需要ReZero：大深度的快速收敛.

Involution: Inverting the Inherence of Convolution for Visual Recognition

Involution：空间独立通道共享的卷积核.

Rethinking the Inception Architecture for Computer Vision

Label Smooth：数据集的标签平滑技巧.

Cascade R-CNN: Delving into High Quality Object Detection

Cascade R-CNN：高质量目标检测研究.