Conditional Convolutional Neural Network for Modality-Aware Face Recognition

Conditional Convolutional Neural Network for Modality-Aware Face Recognition
复制标题

DOI：
10.1109/iccv.2015.418
复制
发表时间：
2015-12
期刊：
2015 IEEE International Conference on Computer Vision (ICCV)
影响因子：
--
通讯作者：
Chao Xiong;Xiaowei Zhao;Danhang Tang;J. Karlekar;Shuicheng Yan;Tae-Kyun Kim
Chao Xiong;Xiaowei Zhao;Danhang Tang;J. Karlekar;Shuicheng Yan;Tae-Kyun Kim
中科院分区：
其他
文献类型：
--
作者：
Chao Xiong;Xiaowei Zhao;Danhang Tang;J. Karlekar;Shuicheng Yan;Tae-Kyun Kim

文献摘要

被引文献

相似文献

野外人脸通常是以各种姿态、光照和遮挡来捕捉的，因此在许多任务中具有固有的多模态分布。我们提出了一个条件卷积神经网络，命名为c-CNN，来处理多模态人脸识别。与采用固定卷积核的传统CNN不同，c-CNN中的样本是用动态激活的核集合来处理的。特别是，当样本通过网络时，每层中的卷积核仅被稀疏地激活。对于给定的样本，特定层中卷积核的激活取决于其当前的中间表示和较低层中的激活状态。跨层激活的内核定义了样本特定的自适应路径，揭示了底层模态的分布。因此，与大多数现有方法相比，拟议的框架不依赖于对模式的任何先验知识。为了证实通用框架，我们通过结合决策树的条件路由来引入c-CNN的一个特殊情况，该情况用多模态的两个问题-多视图人脸识别和遮挡人脸验证来评估。大量的实验表明，一致的改进，同行不知道的方式。
Faces in the wild are usually captured with various poses, illuminations and occlusions, and thus inherently multimodally distributed in many tasks. We propose a conditional Convolutional Neural Network, named as c-CNN, to handle multimodal face recognition. Different from traditional CNN that adopts fixed convolution kernels, samples in c-CNN are processed with dynamically activated sets of kernels. In particular, convolution kernels within each layer are only sparsely activated when a sample is passed through the network. For a given sample, the activations of convolution kernels in a certain layer are conditioned on its present intermediate representation and the activation status in the lower layers. The activated kernels across layers define the sample-specific adaptive routes that reveal the distribution of underlying modalities. Consequently, the proposed framework does not rely on any prior knowledge of modalities in contrast with most existing methods. To substantiate the generic framework, we introduce a special case of c-CNN via incorporating the conditional routing of the decision tree, which is evaluated with two problems of multimodality - multi-view face identification and occluded face verification. Extensive experiments demonstrate consistent improvements over the counterparts unaware of modalities.