Abstract
Recent deep learning based face recognition methods have achieved great performance, but it still remains challenging to recognize very low-resolution query face like 28x28 pixels when CCTV camera is far from the captured subject. Such face with very low-resolution is totally out of detail information of the face identity compared to normal resolution in a gallery and hard to find corresponding faces therein. To this end, we propose a Resolution Invariant Model (RIM) for addressing such cross-resolution face recognition problems, with three distinct novelties. First, RIM is a novel and unified deep architecture, containing a Face Hallucination sub-Net (FHN) and a Heterogeneous Recognition sub-Net (HRN), which are jointly learned end to end. Second, FHN is a well-designed tri-path Generative Adversarial Network (GAN) which simultaneously perceives facial structure and geometry prior information, i.e. landmark heatmaps and parsing maps, incorporated with an unsupervised cross-domain adversarial training strategy to super-resolve very low-resolution query image to its 8x larger ones without requiring them to be well aligned. Third, HRN is a generic Convolutional Neural Network (CNN) for heterogeneous face recognition with our proposed residual knowledge distillation strategy for learning discriminative yet generalized feature representation. Quantitative and qualitative experiments on several benchmarks demonstrate the superiority of the proposed model over the state-of-the-arts. Codes and models will be released upon acceptance.
Abstract (translated)
最近的基于深度学习的人脸识别方法已经取得了很好的效果，但是当闭路电视摄像机远离拍摄对象时，识别像28x28像素这样的低分辨率查询人脸仍然是一个挑战。与画廊中的正常分辨率相比，这种分辨率很低的人脸完全没有人脸身份的细节信息，很难在其中找到相应的人脸。为此，我们提出了一个解决这类跨分辨率人脸识别问题的分辨率不变模型（RIM），它有三个不同的新颖之处。首先，RIM是一种新颖的、统一的深层结构，它包含一个面部幻觉子网（fhn）和一个端到端联合学习的异构识别子网（hrn）。第二，fhn是一个设计良好的三路径生成对抗网络（gan），它同时感知面部结构和几何先验信息，即地标热图和解析地图，与无监督跨域对抗训练策略相结合，以超低分辨率的查询图像解决8倍大的图像，具有很强的灵活性。需要他们很好地协调一致。第三，HRN是一种用于异构人脸识别的通用卷积神经网络（CNN），利用我们提出的剩余知识蒸馏策略来学习识别但又是广义的特征表示。在几个基准上进行的定量和定性实验表明，所提出的模型优于现有技术。代码和型号将在验收后发布。
URL
https://arxiv.org/abs/1905.10777
