Large-Scale R-CNN with Classifier Adaptive Quantization-猫眼课题宝

DOI：

10.1007/978-3-319-46487-9_25

发表时间：

2016-10

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Ryota Hinami;S. Satoh

本文将R-CNN（一种最先进的对象检测方法）扩展到更大的尺度。为了将R-CNN应用于存储数千到数百万图像的大型数据库，从对象提案中提取的数百万到数十亿DCNN特征的SVM分类是必不可少的，这会带来不切实际的计算和内存成本。我们的方法显着缩小了使用倒排索引和有效地搜索使用残差矢量量化（RVQ）的对象建议的数量。而不是k-means已被用于倒排索引，我们提出了一种新的量化方法，设计用于线性分类，其中的量化误差被重新定义为线性分类。该方法利用预先定义的多个样本分类器将误差近似为经验误差，有效地捕捉了对象类别分类器的方差和共同属性。实验结果表明，我们的方法实现了与将R-CNN应用于所有图像相当的性能，同时实现了250倍的加速和180倍的内存减少。此外，我们的方法显着优于最先进的大规模类别检测方法，top-K精度提高了约4058%。可扩展性也得到了验证，我们证明了我们的方法可以在0.13 s内处理100 K图像，同时保持精度。

This paper extends R-CNN, a state-of-the-art object detection method, to larger scales. To apply R-CNN to a large database storing thousands to millions of images, the SVM classification of millions to billions of DCNN features extracted from object proposals is indispensable, which imposes unrealistic computational and memory costs. Our method dramatically narrows down the number of object proposals by using an inverted index and efficiently searches by using residual vector quantization (RVQ). Instead of k-means that has been used in inverted indices, we present a novel quantization method designed for linear classification wherein the quantization error is re-defined for linear classification. It approximates the error as the empirical error with pre-defined multiple exemplar classifiers and captures the variance and common attributes of object category classifiers effectively. Experimental results show that our method achieves comparable performance to that of applying R-CNN to all images while achieving a 250 times speed-up and 180 times memory reduction. Moreover, our approach significantly outperforms the state-of-the-art large-scale category detection method, with about a 4058 % increase in top-K precision. Scalability is also validated, and we demonstrate that our method can process 100 K images in 0.13 s while retaining precision.

Large-Scale R-CNN with Classifier Adaptive Quantization

文献摘要

相似文献