Before entering the neural network, a token is generally converted to the
corresponding one-hot representation, which is a discrete distribution of the
vocabulary. Smoothed representation is the probability of candidate tokens
obtained from a pre-trained masked language model, which can be seen as a more
informative substitution to the one-hot representation. We propose an efficient
data augmentation method, termed text smoothing, by converting a sentence from
its one-hot representation to a controllable smoothed representation. We
evaluate text smoothing on different benchmarks in a low-resource regime.
Experimental results show that text smoothing outperforms various mainstream
data augmentation methods by a substantial margin. Moreover, text smoothing can
be combined with those data augmentation methods to achieve better performance.

该研究提出了一种有效的数据增强方法，又称文本平滑，在神经网络中将一个句子从其单热表示转换为可控的平滑表示，以增强低资源情况下的性能，并发现该方法可以与其他数据增强方法相结合，实现更好的性能。

文本平滑处理：增强文本分类任务中不同的数据增强方法

Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks

Human pose estimation deeply relies on visual clues and anatomical
constraints between parts to locate keypoints. Most existing CNN-based methods
do well in visual representation, however, lacking in the ability to explicitly
learn the constraint relationships between keypoints. In this paper, we propose
a novel approach based on Token representation for human Pose
estimation~(TokenPose). In detail, each keypoint is explicitly embedded as a
token to simultaneously learn constraint relationships and appearance cues from
images. Extensive experiments show that the small and large TokenPose models
are on par with state-of-the-art CNN-based counterparts while being more
lightweight. Specifically, our TokenPose-S and TokenPose-L achieve $72.5$ AP
and $75.8$ AP on COCO validation dataset respectively, with significant
reduction in parameters ($\downarrow80.6\%$; $\downarrow$ $56.8\%$) and GFLOPs
($\downarrow$ $75.3\%$; $\downarrow$ $24.7\%$). Code is publicly available.

本文提出了一种基于 Token 表示的人体姿态估计方法（TokenPose），该方法可以通过学习图像中的外貌线索和约束关系来对关键点进行显式嵌入，与现有 CNN 方法相比，TokenPose 在参数和 GFLOPs 等方面均有所减少，但仍然可以达到与 CNN 的同等水平，代码公开。