论文标题
用于一般对象发现的囊泡视觉变压器
A Saccaded Visual Transformer for General Object Spotting
论文作者
论文摘要
本文介绍了视觉变压器样式贴片分类器的新型组合以及当地的关注。还提供了用于训练对象模型的新型优化范式，而不是优化函数最小化类成员资格概率误差该网络经过训练以估算标记对象的质心的归一化距离。这种方法将一定程度的跨国不变性直接在模型中构建，并允许以梯度上升的快速搜索来查找对象质心。在人的脸上证明了由此产生的囊泡视觉变压器。
This paper presents the novel combination of a visual transformer style patch classifier with saccaded local attention. A novel optimisation paradigm for training object models is also presented, rather than the optimisation function minimising class membership probability error the network is trained to estimate the normalised distance to the centroid of labelled objects. This approach builds a degree of transnational invariance directly into the model and allows fast saccaded search with gradient ascent to find object centroids. The resulting saccaded visual transformer is demonstrated on human faces.
