[Auto-Aug] Scale-aware Automatic Automentation for Object Detection(CVPR. 2021)

最新推荐文章于 2024-02-22 23:52:39 发布

Ah丶Weii

最新推荐文章于 2024-02-22 23:52:39 发布

阅读量659

点赞数 1

分类专栏：学习

本文链接：https://blog.csdn.net/weixin_43823854/article/details/118752974

版权

本文提出了一种新的自动学习尺度感知数据增强策略的方法，针对目标检测和相关框级任务。通过在图像级和框级引入尺度感知，优化了数据增强策略，解决了边界和训练推理差异的问题，提升了尺度适应性。

摘要由CSDN通过智能技术生成

1. Motivation

这篇文章主要关注于目标检测中的数据增强。

This paper focuses on data augmentation for object detection.
之前的工作，对于如何将尺度适应性融入网络的方法主要来源与网络的结构（FPN）以及数据增强。
Previous work handles this challenge which brings the scale adaptation to the network efficiently mainly from two aspects, namely network architecture and data augmentation.
Though inspiring performance gain has achieved, these data augmentation strategies usually rely on heavy expert experience.
Thus, scale-aware property and efficiency issue are essential to address for searching augmentation in box-level tasks.

In this paper, we propose a new way to automatically learn scale-aware data augmentation strategies for object detection and relevant box-level tasks.
We first introduce scale-awareness to the search space from two image-levels and box-levels.

For image-level augmentations, zoom-in and -out operations are included with their probabilities and zooming ratios for search.

For box-level augmentations, the augmenting areas are generalized with a new searchable parameter, i.e., area ratio.