Multicolumn networks for face recognition

Conference item

The objective of this work is set-based face recognition, i.e. to decide if two sets of images of a face are of the same person or not. Conventionally, the set-wise feature descriptor is computed as an average of the descriptors from individual face images within the set. In this paper, we design a neural network architecture that learns to aggregate based on both “visual” quality (resolution, illumination), and “content” quality (relative importance for discriminative classification).

To this end, we propose a Multicolumn Network (MN) that takes a set of images (the number in the set can vary) as input, and learns to compute a fix-sized feature descriptor for the entire set. To encourage high-quality representations, each individual input image is first weighted by its “visual” quality, determined by a self-quality assessment module, and followed by a dynamic recalibration based on “content” qualities relative to the other images within the set. Both of these qualities are learnt implicitly during training for setwise classification. Comparing with the previous state-of-the-art architectures trained with the same dataset (VGGFace2), our Multicolumn Networks show an improvement of between 2-6% on the IARPA IJB face recognition benchmarks, and exceed the state of the art for all methods on these benchmarks.

Authors: Xie, W; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: British Machine Vision Association
• Host title: Proceedings of the 29th British Machine Vision Conference (BMVC 2018)
• Publication date: 2018-09-06
• Acceptance date: 2018-07-02
• Event title: 29th British Machine Vision Conference (BMVC 2018)
• Event location: Newcastle upon Tyne
• Event website: https://bmvc2018.org/
• Event start date: 2018-09-03
• Event end date: 2018-09-06
• Language: English