A Good Practice Towards Top Performance of Face Recognition: Transferred Deep Feature Fusion

Abstract

Unconstrained face recognition performance evaluations have traditionally focused on Labeled Faces in the Wild (LFW) dataset for imagery and the YouTubeFaces (YTF) dataset for videos in the last couple of years. Spectacular progress in this field has resulted in saturation on verification and identification accuracies for those benchmark datasets. In this paper, we propose a unified learning framework named Transferred Deep Feature Fusion (TDFF) targeting at the new IARPA Janus Benchmark A (IJB-A) face recognition dataset released by NIST face challenge. The IJB-A dataset includes real-world unconstrained faces from 500 subjects with full pose and illumination variations which are much harder than the LFW and YTF datasets. Inspired by transfer learning, we train two advanced deep convolutional neural networks (DCNN) with two different large datasets in source domain, respectively. By exploring the complementarity of two distinct DCNNs, deep feature fusion is utilized after feature extraction in target domain. Then, template specific linear SVMs is adopted to enhance the discrimination of framework. Finally, multiple matching scores corresponding different templates are merged as the final results. This simple unified framework exhibits excellent performance on IJB-A dataset. Based on the proposed approach, we have submitted our IJB-A results to National Institute of Standards and Technology (NIST) for official evaluation. Moreover, by introducing new data and advanced neural architecture, our method outperforms the state-of-the-art by a wide margin on IJB-A dataset.

13 pages, 10 figures

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Learning Face Representation from Scratch
• DeepID3: Face Recognition with Very Deep Neural Networks
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
• Representation Learning by Rotating Your Faces
• Towards Large-Pose Face Frontalization in the Wild
• When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition

Cited by in corpus (7)

• Deep Face Recognition: A Survey
• Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
• Families In Wild Multimedia: A Multimodal Database for Recognizing Kinship
• DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
• Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!
• DocFace: Matching ID Document Photos to Selfies
• Automatic Face Understanding: Recognizing Families in Photos