论文标题
使用注意力和软弧线的无监督多对象分割
Unsupervised Multi-object Segmentation Using Attention and Soft-argmax
论文作者
论文摘要
我们介绍了一种新的体系结构，用于无监督对象中心表示学习和多对象检测和分割，该架构使用翻译等值的注意机制来预测场景中存在的对象的坐标并将功能向量与每个对象相关联。变压器编码器处理闭塞和冗余检测，卷积自动编码器负责背景重建。我们表明，这种体系结构在复杂的合成基准上大大优于最新技术。
We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present in the scene and to associate a feature vector to each object. A transformer encoder handles occlusions and redundant detections, and a convolutional autoencoder is in charge of background reconstruction. We show that this architecture significantly outperforms the state of the art on complex synthetic benchmarks.
