Learning Unified Representations for Multi-Resolution Face Recognition
This addresses face recognition challenges in scenarios with varying image resolutions, such as surveillance, though it is an incremental improvement over existing methods.
The paper tackles the problem of multi-resolution face recognition by proposing the Branch-to-Trunk network (BTNet), which improves discriminability for tiny faces by mitigating interpolation errors from rescaling, achieving new state-of-the-art results on the QMUL-SurvFace benchmark.
In this work, we propose Branch-to-Trunk network (BTNet), a representation learning method for multi-resolution face recognition. It consists of a trunk network (TNet), namely a unified encoder, and multiple branch networks (BNets), namely resolution adapters. As per the input, a resolution-specific BNet is used and the output are implanted as feature maps in the feature pyramid of TNet, at a layer with the same resolution. The discriminability of tiny faces is significantly improved, as the interpolation error introduced by rescaling, especially up-sampling, is mitigated on the inputs. With branch distillation and backward-compatible training, BTNet transfers discriminative high-resolution information to multiple branches while guaranteeing representation compatibility. Our experiments demonstrate strong performance on face recognition benchmarks, both for multi-resolution identity matching and feature aggregation, with much less computation amount and parameter storage. We establish new state-of-the-art on the challenging QMUL-SurvFace 1: N face identification task. Our code is available at https://github.com/StevenSmith2000/BTNet.