Company News

Conditional Convolutional Neural Network for Modality-Aware Face Recognition

|

Chao Xiong, Xiaowei Zhao, Danhang Tang, Jayashree Karlekar, Shuicheng Yan, Tae-Kyun Kim
International Conference on Computer Vision (ICCV), 2015.12

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.

Link: https://ieeexplore.ieee.org/document/7410775

Share

Related Posts

Panasonic launched a “Panasonic Deep Tech Innovation Challenge” inviting local start-ups to leverage Panasonic’s technology & patents for business creation

Panasonic R&D Center Singapore has launched a Panasonic Deep Tech Innovation Challenge organized by Panasonic, ICMG and ACE. This Challenge…

Read more

Panasonic R&D Center Singapore (PRDCSG) participated in the ITS World Congress 2019

Joining Panasonic’s booth at the ITS World Congress 2019 held at Suntec City of Singapore from October 21st to October…

Read more

Paper accepted for publication in the special issue of the IEEE Transactions on Circuits and Systems for Video Technology

Teaming up with several world-renowned video experts, Panasonic R&D Center Singapore co-authored a paper titled “General Video Coding Technology in…

Read more

Panasonic ranked #1 in Mugshot category of NIST FRVT 1:1 Challenge

PRDCSG once again kept Panasonic’s flag flying high in the global arena. In the latest Performance Summary of the NIST*…

Read more