Much work has been devoted to devising architectures that build
group-equivariant representations, while invariance is often induced using
simple global pooling mechanisms. Little work has been done on creating
<
本文介绍了一种名为 Group Invariant Feature Transform (GIFT) 的可区分性强、鲁棒性强的视觉描述符,其利用基于组的卷积提取从图像的转换版本中提取的特征信息,相对于聚合特征的方法,GIFT 对于一组变换有证明的不变性,实验表明 GIFT 在多个基准数据集上优于现有的方法,可以实现相对位姿估计的实用性改进。