Multicolumn Networks for Face Recognition

TL;DR

This paper introduces a Multicolumn Network architecture for set-based face recognition that learns to weight images by visual and content quality, improving recognition accuracy over previous methods.

Contribution

The paper proposes a novel neural network that adaptively aggregates face images based on learned quality assessments, enhancing set-wise face recognition performance.

Findings

Achieves 2-6% improvement on IJB face recognition benchmarks.

Outperforms previous state-of-the-art methods on these benchmarks.

Learns implicit quality measures for better feature aggregation.

Abstract

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 set-wise 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.