arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.06010cs.CV
收藏

BranchConnect:学习分支连接的大规模视觉识别

BranchConnect: Large-Scale Visual Recognition with Learned Branch Connections

Dartmouth College(达特茅斯学院)

Karim Ahmed, Lorenzo Torresani

摘要:

我们介绍了一个大规模图像分类的架构,使端到端的学习单独的视觉功能,为不同的类来区分。所提出的模型由一个深CNN形状像一棵树。树的主干包括所有类共有的卷积层序列。然后,主干分成多个分支,实现并行特征提取器,这些特征提取器最终通过学习的门控连接连接到最终分类层。这些学习的门为每个单独的类确定要使用的特征子集。这样的方案自然鼓励通过单独的分支来学习一组异构的专门特征,并且它允许每个类使用对其识别最优的特征子集。我们通过将文献中的几种流行的CNN重塑为我们提出的架构来展示我们提出的方法的通用性。我们在CIFAR100、CIFAR10和Synth数据集上的实验表明,在每种情况下,我们的模型在准确性上都比原始CNN有了实质性的提高。我们的实证分析还表明,我们的计划作为一种有益的正则化形式,提高泛化性能。

英文摘要:

We introduce an architecture for large-scale image categorization that enables the end-to-end learning of separate visual features for the different classes to distinguish. The proposed model consists of a deep CNN shaped like a tree. The stem of the tree includes a sequence of convolutional layers common to all classes. The stem then splits into multiple branches implementing parallel feature extractors, which are ultimately connected to the final classification layer via learned gated connections. These learned gates determine for each individual class the subset of features to use. Such a scheme naturally encourages the learning of a heterogeneous set of specialized features through the separate branches and it allows each class to use the subset of features that are optimal for its recognition. We show the generality of our proposed method by reshaping several popular CNNs from the literature into our proposed architecture. Our experiments on the CIFAR100, CIFAR10, and Synth datasets show that in each case our resulting model yields a substantial improvement in accuracy over the original CNN. Our empirical analysis also suggests that our scheme acts as a form of beneficial regularization improving generalization performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑