论文标题
视觉识别的亲和力图监督
Affinity Graph Supervision for Visual Recognition
论文作者
论文摘要
亲和力图广泛用于深度体系结构，包括图形卷积神经网络和注意力网络。到目前为止，文献一直集中在这些图形中的抽象特征上，而对亲和力本身的学习被忽略了。在这里，我们提出了一种原则性的方法，可以直接监督亲和力图中的权重学习，以利用数据源中实体之间有意义的联系。应用于视觉注意网络，即使没有手动注释的关系标签，我们的亲和力监督也可以改善对象之间的关系恢复。我们进一步表明，对象之间的亲和力学习提高了场景分类性能，并且对亲和力的监督也可以应用于通过迷你批次构建的图表进行神经网络培训。在图像分类任务中，我们通过不同的网络体系结构和数据集证明了对基线的一致改进。
Affinity graphs are widely used in deep architectures, including graph convolutional neural networks and attention networks. Thus far, the literature has focused on abstracting features from such graphs, while the learning of the affinities themselves has been overlooked. Here we propose a principled method to directly supervise the learning of weights in affinity graphs, to exploit meaningful connections between entities in the data source. Applied to a visual attention network, our affinity supervision improves relationship recovery between objects, even without the use of manually annotated relationship labels. We further show that affinity learning between objects boosts scene categorization performance and that the supervision of affinity can also be applied to graphs built from mini-batches, for neural network training. In an image classification task we demonstrate consistent improvement over the baseline, with diverse network architectures and datasets.
