期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 40, 期 6, 页码 1309-1322出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2017.2723400
关键词
Fine-grained recognition; texture representations; second order pooling; bilinear models; convolutional networks
资金
- Office of the Director of National Intelligence (ODNI)
- Intelligence Advanced Research Projects Activity (IARPA) [2014-14071600010]
- National Science Foundation [IIS-1617917]
We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1, 79.4, 84.5 and 91.3 percent per-image accuracy on the Caltech-UCSD birds [1], NABirds [2], FGVC aircraft [3], and Stanford cars [4] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据