arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1505.02269cs.CV
收藏

细粒度类别分类的子集特征学习

Subset Feature Learning for Fine-Grained Category Classification

Australian Centre for Robotic Vision(澳大利亚机器人视觉中心);Queensland University of Technology(昆士兰科技大学);University of Queensland(昆士兰大学);NICTA

Zongyuan Ge, Christopher Mccool, Conrad Sanderson, Peter Corke

摘要:

细粒度分类一直是一个具有挑战性的问题,由于类间变化小,类内变化大,训练图像的数量少。我们提出了一个学习系统,它首先聚类视觉上相似的类,然后学习特定于每个子集的深度卷积神经网络特征。在流行的细粒度Caltech-UCSD鸟类数据集上的实验表明,该方法在最困难的设置下优于最近的细粒度分类方法:在测试时没有边界框。它的平均准确率为77.5%,而之前的最佳性能为73.2%。我们还表明,渐进式迁移学习允许我们首先学习域通用功能(用于鸟类分类),然后可以适应特定的鸟类类集,从而提高准确性。

英文摘要:

Fine-grained categorisation has been a challenging problem due to small inter-class variation, large intra-class variation and low number of training images. We propose a learning system which first clusters visually similar classes and then learns deep convolutional neural network features specific to each subset. Experiments on the popular fine-grained Caltech-UCSD bird dataset show that the proposed method outperforms recent fine-grained categorisation methods under the most difficult setting: no bounding boxes are presented at test time. It achieves a mean accuracy of 77.5%, compared to the previous best performance of 73.2%. We also show that progressive transfer learning allows us to first learn domain-generic features (for bird classification) which can then be adapted to specific set of bird classes, yielding improvements in accuracy.

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。

↑